© 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. 216739
    Prev
    Next
    INDEX
    Explanations

    games and opportunities

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

    handles ... for

    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
    owej
    0.50
     данной
    0.49
    ッジ
    0.47
    owym
    0.46
    igten
    0.45
    갇
    0.45
     ונ
    0.45
    品种
    0.44
     Parmesan
    0.44
    文化的
    0.44
    POSITIVE LOGITS
     calls
    0.46
    LAW
    0.46
    elie
    0.46
    onto
    0.43
    Calls
    0.42
    章
    0.42
    حده
    0.42
     reminding
    0.42
    ૂર્ણ
    0.42
    क्रिया
    0.42
    Activations Density 0.000%

    No Known Activations