© 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. 22-GEMMASCOPE-RES-131K
    4. 95437
    Prev
    Next
    INDEX
    Explanations

    Python class and module definitions

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

    The neuron activates on numeric tokens—like version numbers, constants, addresses, or other digit‐only strings—wherever they appear.

    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
     its
    -1.25
     one
    -1.20
    に行きました
    -0.98
    境的
    -0.94
     or
    -0.94
    の関係
    -0.91
     from
    -0.91
    ̗
    -0.90
    Страна
    -0.90
    {{--
    -0.90
    POSITIVE LOGITS
    ׳
    1.35
    Ͳ
    1.19
    preneur
    1.16
    preneurs
    1.13
    ├
    1.13
     pagare
    1.06
    tious
    1.05
    lysm
    1.04
     MATTERS
    1.04
    quared
    1.04
    Activations Density 0.004%

    No Known Activations