© 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. 189000
    Prev
    Next
    INDEX
    Explanations

    sales and offers

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

    specific nouns and concepts

    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
     activar
    0.51
     filoz
    0.44
     absolutamente
    0.43
    yfik
    0.43
    圩
    0.43
     ništa
    0.42
     Blanca
    0.40
    -*/
    0.40
     Bxa
    0.40
    🐇
    0.40
    POSITIVE LOGITS
     신
    0.46
     에
    0.45
    spann
    0.45
    thu
    0.45
    prf
    0.45
    ong
    0.44
    llen
    0.44
    uper
    0.44
    ibe
    0.43
    ul
    0.43
    Activations Density 0.005%

    No Known Activations