© 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. 32820
    Prev
    Next
    INDEX
    Explanations

    properly installed

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

    harming, domination, deceive

    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
     hè
    0.44
    टीएम
    0.43
     épisode
    0.43
    馋
    0.42
    ভক্ত
    0.42
    ĐT
    0.41
    TR
    0.41
     Episode
    0.41
     thương
    0.40
     Thương
    0.40
    POSITIVE LOGITS
    гем
    0.44
    समझ
    0.43
     bundling
    0.40
     proportionate
    0.39
     réaliser
    0.39
    gekehrt
    0.39
    ੰਜ
    0.39
     ।,
    0.39
     »
    0.38
    atual
    0.38
    Activations Density 0.000%

    No Known Activations