© 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. 199791
    Prev
    Next
    INDEX
    Explanations

    attachment/association

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

    handling complexity and difficulty

    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
     뛰
    0.51
    Byte
    0.46
    कंप
    0.46
     உதவு
    0.45
    through
    0.45
    돕
    0.44
    boldsymbol
    0.44
    ನಿರ್
    0.44
    व
    0.44
    across
    0.44
    POSITIVE LOGITS
     weddings
    0.53
     cigarettes
    0.52
     ferries
    0.47
     csak
    0.46
     ventilation
    0.45
     clamps
    0.45
     fucking
    0.45
     villas
    0.45
     saliva
    0.45
     الطعام
    0.45
    Activations Density 0.000%

    No Known Activations