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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1803
    Prev
    Next
    INDEX
    Explanations

    python super calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     తగ్
    0.44
    塹
    0.43
    ボー
    0.42
    tStart
    0.42
    akim
    0.40
     pivoted
    0.39
     ボー
    0.39
    gateTime
    0.39
    縈
    0.39
    澼
    0.38
    POSITIVE LOGITS
     super
    1.82
    super
    1.80
     супер
    1.46
     सुपर
    1.38
     Super
    1.37
    Super
    1.28
    超级
    1.20
     súper
    1.20
    スーパー
    1.19
     슈퍼
    1.16
    Activations Density 0.014%

    No Known Activations