© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32958
    Prev
    Next
    INDEX
    Explanations

    listing disallowed sexual acts

    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
    तरा
    0.52
    ii
    0.43
     gens
    0.41
     Corps
    0.40
    reathe
    0.40
    ĺ
    0.39
     Circle
    0.39
    сшта
    0.39
    ä
    0.39
    ிற
    0.38
    POSITIVE LOGITS
     또는
    0.53
     혹은
    0.52
     ataupun
    0.50
     அல்லது
    0.49
     hoặc
    0.48
    或其他
    0.46
     ಅಥವಾ
    0.45
     asociación
    0.45
     или
    0.44
     లేదా
    0.44
    Activations Density 0.190%

    No Known Activations