© 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. 30230
    Prev
    Next
    INDEX
    Explanations

    rape and me

    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
     y
    0.48
     dj
    0.45
     foundations
    0.41
     iar
    0.41
     da
    0.40
     in
    0.39
     zu
    0.39
     leagues
    0.39
     class
    0.39
     h
    0.38
    POSITIVE LOGITS
     описание
    0.55
     सत्यापन
    0.53
     générateur
    0.49
     остальные
    0.46
    藠
    0.46
     删除
    0.45
     остальных
    0.45
    HttpPut
    0.45
     решение
    0.44
    Descripción
    0.44
    Activations Density 0.001%

    No Known Activations