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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11306
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    '
    -1.57
    ’
    -1.33
    ,
    -1.33
    -
    -1.28
    <>
    
    -1.26
    ковая
    -1.20
     teneur
    -1.16
     ランド
    -1.14
     фотография
    -1.13
    e
    -1.13
    POSITIVE LOGITS
     and
    2.48
     which
    2.39
     or
    2.31
     including
    1.55
    angkap
    1.36
     וכן
    1.35
     மற்றும்
    1.29
     this
    1.23
     such
    1.20
     where
    1.16
    Activations Density 0.095%

    No Known Activations