© 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. 216973
    Prev
    Next
    INDEX
    Explanations

    same service

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

    report structure

    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
    -
    0.56
    ческих
    0.48
    两人
    0.45
    constraintTop
    0.43
     పెట్టు
    0.42
    在线
    0.42
    两
    0.42
     четырех
    0.41
     двух
    0.41
     трех
    0.41
    POSITIVE LOGITS
     Лі
    0.52
     രാ
    0.51
     那麼
    0.48
     숨
    0.47
    Hmmm
    0.47
     พิจ
    0.47
     sentences
    0.46
     Soldaten
    0.46
    દો
    0.46
    あっ
    0.45
    Activations Density 0.001%

    No Known Activations