© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8201
    Prev
    Next
    INDEX
    Explanations

    two letter codes

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

    codes and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stateMutability
    0.43
    簋
    0.42
    碛
    0.41
    UIntValue
    0.39
    χαν
    0.38
    厦
    0.38
    ֒
    0.38
    slideDuplicate
    0.38
     हिस
    0.38
    敔
    0.38
    POSITIVE LOGITS
     FP
    2.59
     JP
    2.55
     BP
    2.52
    JP
    2.48
    FP
    2.45
     RP
    2.44
    BP
    2.41
     DP
    2.39
     LP
    2.38
     KP
    2.38
    Activations Density 0.432%

    No Known Activations