© 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. 117072
    Prev
    Next
    INDEX
    Explanations

    not a, more, really

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

    case of

    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
     Asiatic
    0.40
    olyte
    0.39
     [&
    0.37
    imdi
    0.36
    pretty
    0.35
     Aku
    0.34
     знамени
    0.34
     \\
    0.34
    we
    0.34
    addon
    0.34
    POSITIVE LOGITS
     mencionó
    0.47
     वैसा
    0.46
     তুলনা
    0.45
     lenne
    0.45
     necesariamente
    0.43
     necessariamente
    0.42
     "`
    0.41
     غلط
    0.41
    לות
    0.40
    ोनेशिया
    0.40
    Activations Density 0.130%

    No Known Activations