© 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. 203192
    Prev
    Next
    INDEX
    Explanations

    listed under category

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

    summarizing in, beyond the, Circle:, within her, coaches, calling

    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
     BIP
    0.47
     mental
    0.47
    },
    0.47
     Mitra
    0.42
     Serial
    0.41
     simultaneous
    0.41
     graveyard
    0.40
     Father
    0.40
     headed
    0.40
     ritual
    0.39
    POSITIVE LOGITS
    紅
    0.49
    高峰
    0.49
    ADE
    0.48
     जिसमें
    0.47
    ují
    0.47
     والتي
    0.47
     والذي
    0.47
    ęła
    0.47
    òng
    0.47
    aleigh
    0.47
    Activations Density 0.000%

    No Known Activations