© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43355
    Prev
    Next
    INDEX
    Explanations

    locations like New York

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

    using calculations

    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
    σα
    0.52
    ಾಯಕ
    0.49
    ghar
    0.46
    bücher
    0.44
    hadas
    0.44
    v
    0.43
     ର
    0.43
    白的
    0.42
    vak
    0.42
    schl
    0.41
    POSITIVE LOGITS
    উঠ
    0.49
    </h3>
    0.48
    幼稚園
    0.45
    പ്പാ
    0.44
     புரிந்து
    0.44
     दोन
    0.44
     telefoon
    0.43
    </h4>
    0.42
    ത്തോടെ
    0.42
     troop
    0.41
    Activations Density 0.000%

    No Known Activations