© 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. 76903
    Prev
    Next
    INDEX
    Explanations

    incest and child abuse

    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
     Structure
    0.46
     contributes
    0.45
     Stru
    0.45
     defines
    0.44
     Hyper
    0.43
     Montevideo
    0.43
    r
    0.43
     sits
    0.41
     explains
    0.41
     solves
    0.40
    POSITIVE LOGITS
    Фі
    0.53
    Pclass
    0.52
    يد
    0.52
     merav
    0.52
    ോട്ടോ
    0.52
    희
    0.52
     poo
    0.50
     pajak
    0.50
    Transaksi
    0.49
     scelto
    0.49
    Activations Density 0.004%

    No Known Activations