© 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. 37080
    Prev
    Next
    INDEX
    Explanations

    explaining complex or specific topics

    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
    ा
    0.52
    ها
    0.48
    ية
    0.48
     exceptions
    0.47
     commandments
    0.45
     flexibilidad
    0.44
     excepciones
    0.44
     poisoning
    0.43
     modification
    0.42
     flexibility
    0.42
    POSITIVE LOGITS
     nostalg
    0.63
    🥳
    0.60
     reminis
    0.54
     музыку
    0.53
    🥸
    0.53
     nostalgic
    0.50
     racconta
    0.50
    🥹
    0.50
     पुराना
    0.49
     Metaverse
    0.49
    Activations Density 0.001%

    No Known Activations