© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4032
    Prev
    Next
    INDEX
    Explanations

    rape word component

    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_40_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
    Gé
    0.44
    lovl
    0.42
     fech
    0.42
    נה
    0.38
     strolling
    0.38
     stroll
    0.37
     toler
    0.37
    კ
    0.37
     Ге
    0.37
     열
    0.36
    POSITIVE LOGITS
    ágina
    0.41
     انقلاب
    0.39
    键
    0.38
     '//
    0.37
     PPM
    0.37
    ➽
    0.37
     মাটি
    0.37
     Revolution
    0.37
     Deformation
    0.37
    azine
    0.36
    Activations Density 0.004%

    No Known Activations