© 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-65K
    7. 40488
    Prev
    Next
    INDEX
    Explanations

    security considerations and risks

    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_65k_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
    '
    0.92
    "
    0.88
    ス
    0.88
    在
    0.81
    }=
    0.79
    ب
    0.79
    ”
    0.79
    كور
    0.75
    кої
    0.75
    ี
    0.71
    POSITIVE LOGITS
    et
    0.74
    your
    0.71
    such
    0.68
    rt
    0.66
    lt
    0.66
    lock
    0.66
    니
    0.65
    love
    0.64
    ere
    0.63
    that
    0.63
    Activations Density 0.052%

    No Known Activations