© 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. 21530
    Prev
    Next
    INDEX
    Explanations

    avoid contributing

    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
     in
    0.55
     extracted
    0.55
     sass
    0.54
     flipped
    0.53
    筤
    0.51
     votre
    0.50
     ваша
    0.50
     faulted
    0.50
     interpreted
    0.49
     αν
    0.48
    POSITIVE LOGITS
    Avoid
    0.98
    avoid
    0.98
     avoid
    0.96
    避免
    0.94
    避
    0.93
     avoids
    0.88
     Avoid
    0.82
     evitando
    0.82
    Avoiding
    0.82
     tránh
    0.79
    Activations Density 0.047%

    No Known Activations