© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23712
    Prev
    Next
    INDEX
    Explanations

    genuinely malicious, greater than, constantly asked

    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
     general
    0.45
    prime
    0.44
     humanity
    0.43
    disciplinary
    0.39
    Γ
    0.39
    <0x0D>
    0.39
     wrote
    0.39
    "
    0.38
    없
    0.38
     ;
    0.37
    POSITIVE LOGITS
    锜
    0.45
    ുവരി
    0.44
    𝗎
    0.42
    wiches
    0.42
    둴
    0.41
     états
    0.41
    💵
    0.41
    कियां
    0.41
     নিঃসৃত
    0.41
    aing
    0.41
    Activations Density 0.000%

    No Known Activations