© 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. 91167
    Prev
    Next
    INDEX
    Explanations

    numbers generates

    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
     Dé
    0.49
     recort
    0.45
     Bower
    0.44
     lé
    0.44
    r
    0.43
     období
    0.42
     Zing
    0.42
    azität
    0.41
     números
    0.41
     představ
    0.40
    POSITIVE LOGITS
    スープ
    0.50
    供給
    0.47
    ifera
    0.47
    ドリ
    0.46
    在我们
    0.46
    を提供
    0.46
    も
    0.45
    コスメ
    0.45
    もら
    0.45
    stedt
    0.44
    Activations Density 0.005%

    No Known Activations