© 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. 150243
    Prev
    Next
    INDEX
    Explanations

    past the fresh stage

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

    container types, tech terms, food items

    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
    id
    0.55
    eq
    0.44
    epid
    0.44
    Epid
    0.43
    k
    0.43
    竹
    0.43
     antibiotics
    0.43
    odh
    0.43
     diuretics
    0.43
     Epid
    0.42
    POSITIVE LOGITS
     contraste
    0.49
    gré
    0.48
     abrir
    0.47
    grin
    0.47
     é
    0.47
     arriba
    0.46
     apie
    0.46
     engen
    0.46
     clairement
    0.46
     estadounidense
    0.46
    Activations Density 0.000%

    No Known Activations