© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30599
    Prev
    Next
    INDEX
    Explanations

    likely followed by prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ti
    0.71
    த்தில்
    0.71
     Είναι
    0.68
    л
    0.65
    ﺘ
    0.65
    ről
    0.63
    rul
    0.62
    sk
    0.61
    rä
    0.61
    tiin
    0.61
    POSITIVE LOGITS
     to
    0.89
    on
    0.78
    на
    0.76
    u
    0.73
    in
    0.72
    et
    0.72
    uí
    0.66
    hood
    0.63
    㵴
    0.62
    hi
    0.61
    Activations Density 0.042%

    No Known Activations