© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 41926
    Prev
    Next
    INDEX
    Explanations

    exploit, abuse, endanger

    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
    ные
    0.63
    3
    0.57
    OF
    0.57
     Австра
    0.56
     غير
    0.52
     Му
    0.52
    ли
    0.52
     Нор
    0.52
    averaged
    0.52
     بيان
    0.52
    POSITIVE LOGITS
     explo
    0.65
     explot
    0.64
     a
    0.58
     exploitation
    0.57
     pasar
    0.57
     leverages
    0.57
     minat
    0.56
     exploit
    0.55
     the
    0.55
     restaur
    0.55
    Activations Density 0.053%

    No Known Activations