© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165001
    Prev
    Next
    INDEX
    Explanations

    use your knowledge punish

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

    disclaimers and consensual content

    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_31_width_262k_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
    ว์
    0.45
     выполнен
    0.45
    -
    0.45
    Position
    0.44
     continu
    0.43
     Recon
    0.41
     Gymnasium
    0.41
    Displayed
    0.40
     Ausbildung
    0.40
     spinster
    0.40
    POSITIVE LOGITS
     کافی
    0.50
    obeb
    0.47
     hebat
    0.47
    โก
    0.46
     ilustração
    0.45
     maggior
    0.45
    撗
    0.44
    illust
    0.44
    रविवार
    0.44
    خی
    0.42
    Activations Density 0.000%

    No Known Activations