© 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. 19005
    Prev
    Next
    INDEX
    Explanations

    returning or giving back

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

    code documentation comments

    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
    窣
    0.43
    স্পতিবার
    0.42
    ত্যার
    0.41
     কাঁদতে
    0.40
    த்துவம்
    0.39
    )[
    0.39
     Anything
    0.39
     exemples
    0.39
     sasane
    0.39
    Ს
    0.38
    POSITIVE LOGITS
    family
    0.49
     family
    0.45
     lu
    0.44
    char
    0.43
    des
    0.42
    big
    0.41
    idea
    0.39
    &
    0.39
    biggest
    0.38
     naj
    0.38
    Activations Density 0.000%

    No Known Activations