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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 13402
    Prev
    Next
    INDEX
    Explanations

    domestic violence hotline SAFE

    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
     dividend
    0.48
    dividend
    0.40
     Dividend
    0.39
     Redeem
    0.39
     sci
    0.38
     MORT
    0.38
    饋
    0.37
     편
    0.37
     ciencia
    0.37
     glum
    0.37
    POSITIVE LOGITS
     abusive
    1.23
     abuse
    1.20
    Domestic
    1.20
     abusers
    1.19
     Domestic
    1.17
     victim
    1.16
     Abuse
    1.15
     domestic
    1.12
     victims
    1.12
     abused
    1.09
    Activations Density 0.116%

    No Known Activations