© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 196910
    Prev
    Next
    INDEX
    Explanations

    status of partner

    np_acts-logits-general · gemini-2.5-flash-lite

    responding with refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ቓ
    0.56
     ब्राह
    0.54
    algèbre
    0.52
     गोइंग
    0.51
    ומ
    0.51
    ទំនាក់
    0.50
     डाइजेस्टिव
    0.50
    Cnt
    0.50
     करिकुलम
    0.49
     венти
    0.49
    POSITIVE LOGITS
     ”
    0.53
     https
    0.50
     ©
    0.49
     placer
    0.49
     £
    0.47
     sker
    0.47
    0.46
     producer
    0.45
     c
    0.45
     fc
    0.45
    Activations Density 0.000%

    No Known Activations