© 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. 36140
    Prev
    Next
    INDEX
    Explanations

    unforeseen consequences or misuse

    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
    な
    0.47
    си
    0.47
    защи
    0.42
     literate
    0.41
    도
    0.41
    ፀ
    0.41
    ENE
    0.41
    ጸ
    0.41
    とも
    0.40
     especific
    0.40
    POSITIVE LOGITS
     CaCO
    0.48
     yogurt
    0.46
     beige
    0.45
     popsicle
    0.45
     epicenter
    0.43
    pstmt
    0.43
    scattering
    0.43
     centerline
    0.43
    🕋
    0.42
    ্যান্ড
    0.41
    Activations Density 0.003%

    No Known Activations