© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    code and configuration"}

    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
    ৄ
    -2.34
    ৹
    -2.31
    鬭
    -2.16
    
    -2.09
     bym
    -2.03
    𞤤
    -1.93
    裢
    -1.88
    ༵
    -1.87
    Ꮄ
    -1.86
    けない
    -1.83
    POSITIVE LOGITS
     
    1.77
     –
    1.58
    –
    1.54
    J
    1.53
    _
    1.52
    !
    1.51
    th
    1.48
    ent
    1.45
    ons
    1.43
    ppure
    1.39
    Activations Density 0.005%

    No Known Activations