© 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. 110387
    Prev
    Next
    INDEX
    Explanations

    discovery

    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
    ovaniyu
    0.56
    ří
    0.53
    ó
    0.51
    óry
    0.50
    kov
    0.49
    tow
    0.48
     पादुकोण
    0.48
    kében
    0.47
    uldron
    0.46
    hört
    0.45
    POSITIVE LOGITS
     omnichannel
    0.50
     navigation
    0.46
     Facebook
    0.45
     monotonic
    0.44
     Norwegian
    0.43
     authenticity
    0.42
    3
    0.42
     Oslo
    0.42
     SSI
    0.42
     CCL
    0.42
    Activations Density 0.004%

    No Known Activations