© 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-262K
    7. 47815
    Prev
    Next
    INDEX
    Explanations

    allowable output, mortgage, progress, coordinates, nervously

    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_262k_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
     että
    0.50
     dass
    0.49
     voul
    0.49
     هناك
    0.49
    Pip
    0.46
    厝
    0.46
     کہ
    0.45
    Harm
    0.44
    Hlav
    0.44
    ഘടന
    0.44
    POSITIVE LOGITS
    de
    0.44
    nil
    0.42
    ﮏ
    0.42
     সত্ত্বেও
    0.41
    các
    0.41
    childNodes
    0.40
    deselect
    0.40
     nonnegative
    0.39
     transfers
    0.39
    ugawa
    0.39
    Activations Density 0.002%

    No Known Activations