© 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. 127803
    Prev
    Next
    INDEX
    Explanations

    partnership and API updates

    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
    s
    0.54
    с
    0.47
    kowitz
    0.46
     RMSE
    0.46
    ре
    0.43
    ाइ
    0.43
     glycemic
    0.43
     cortisol
    0.42
    та
    0.42
     QTL
    0.41
    POSITIVE LOGITS
     ambos
    0.49
     Resist
    0.47
     goles
    0.46
    Ꮟ
    0.44
     novos
    0.43
     étaient
    0.42
     Fittings
    0.42
     എന്നാൽ
    0.42
     sólidos
    0.42
    𝘇
    0.42
    Activations Density 0.001%

    No Known Activations