© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12238
    Prev
    Next
    INDEX
    Explanations

    chaining

    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
    .
    -3.77
    也很
    -2.41
     continually
    -2.36
     Flasche
    -2.30
     kleines
    -2.23
    缡
    -2.19
    為に
    -2.17
    椟
    -2.16
    …….
    -2.14
    pecabe
    -2.14
    POSITIVE LOGITS
    ～～
    2.67
    движи
    2.64
    婓
    2.56
    で
    2.53
    ～～～
    2.42
     desee
    2.30
     permita
    2.28
    数を
    2.25
     stellen
    2.23
     говорить
    2.22
    Activations Density 0.011%

    No Known Activations