© 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. 12234
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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
    鵙
    -1.90
    usions
    -1.82
     花纹
    -1.71
    roslav
    -1.70
    uded
    -1.70
    绡
    -1.69
    儇
    -1.66
    ーズン
    -1.59
    鶇
    -1.58
    ⭓
    -1.54
    POSITIVE LOGITS
    x
    1.51
    man
    1.47
    as
    1.43
    l
    1.41
     gets
    1.40
     always
    1.39
    ”,
    1.38
    ↵
    1.37
     can
    1.35
    and
    1.32
    Activations Density 0.009%

    No Known Activations