© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118922
    Prev
    Next
    INDEX
    Explanations

    fruit and bearing

    np_acts-logits-general · gemini-2.5-flash-lite

    references to "fruit" or "bearing fruit" in both literal and metaphorical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags words and phrases that denote something produced or yielded—offspring or results—such as “children of,” “bear fruit,” and “fruit of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rengi
    -1.29
    el
    -1.25
    </h3>
    -1.24
    Seine
    -1.23
     how
    -1.22
    or
    -1.19
    __;
    -1.18
    and
    -1.16
    Ꭱ
    -1.13
     другими
    -1.10
    POSITIVE LOGITS
     only
    1.52
     pouze
    1.35
     тільки
    1.34
    に限
    1.26
     tohoto
    1.23
     Apenas
    1.23
    voller
    1.22
    寧
    1.22
     pomys
    1.20
    艽
    1.20
    Activations Density 0.028%

    No Known Activations