© 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. 42089
    Prev
    Next
    INDEX
    Explanations

    security and coding

    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
    ス
    0.88
    在
    0.86
    '
    0.81
     σε
    0.80
    }=
    0.80
    "
    0.79
    َة
    0.77
    ী
    0.77
    كور
    0.76
    zieć
    0.75
    POSITIVE LOGITS
    et
    0.84
     보안
    0.81
     säker
    0.79
     seguridad
    0.77
    your
    0.77
     insecure
    0.72
    rt
    0.70
    lt
    0.69
    ro
    0.68
     on
    0.68
    Activations Density 0.048%

    No Known Activations