© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 158
    Prev
    Next
    INDEX
    Explanations

    directory, platform, use, attempts, prints, handle, between, model

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

    The neuron fires on human‐readable documentation strings or help text in code/config files (e.g. descriptions, docstrings, usage messages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    >*/
    -1.20
     flä
    -1.18
     his
    -1.10
     this
    -1.06
    altezza
    -1.03
     jugend
    -1.02
    لغة
    -1.02
    =“
    -1.02
     kopf
    -1.00
    readFileSync
    -1.00
    POSITIVE LOGITS
     to
    1.51
    𝒙
    1.23
    Біографія
    1.21
    𝘩
    1.21
     you
    1.17
     DialogResult
    1.12
    即便
    1.09
     требуется
    1.09
     подойдет
    1.07
    sió
    1.06
    Activations Density 0.012%

    No Known Activations