© 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. 53-GEMMASCOPE-2-RES-262K
    7. 19947
    Prev
    Next
    INDEX
    Explanations

    sexual assault hotline

    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_53_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
    }--\
    0.41
    リン
    0.41
     rage
    0.38
     disappoint
    0.38
     সেপ্ট
    0.37
     limp
    0.37
     doves
    0.37
    裕
    0.36
    Dict
    0.36
    傾
    0.36
    POSITIVE LOGITS
    autom
    0.42
     Such
    0.42
     *****
    0.41
     Skid
    0.41
     .”
    0.41
     More
    0.40
    Such
    0.39
    سل
    0.38
     முடிய
    0.38
     Hail
    0.38
    Activations Density 0.009%

    No Known Activations