© 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. 191829
    Prev
    Next
    INDEX
    Explanations

    free postcard, severe clinical signs, double walls

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

    emblems Security

    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
    t
    0.78
    gg
    0.67
    is
    0.66
    3
    0.65
    ag
    0.64
    ng
    0.64
    we
    0.63
    m
    0.63
    with
    0.63
    n
    0.63
    POSITIVE LOGITS
    ジネス
    0.48
     امنیت
    0.47
     semilla
    0.46
    狄
    0.46
    یداری
    0.46
     đòi
    0.46
     incluyendo
    0.45
     cultivos
    0.45
     včetně
    0.45
    ัตว์
    0.44
    Activations Density 0.000%

    No Known Activations