© 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. 100949
    Prev
    Next
    INDEX
    Explanations

    AI advancement and society

    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
    ENCE
    0.45
     समस्या
    0.45
     "/
    0.43
     Restore
    0.43
    Leftrightarrow
    0.42
     जीतकर
    0.41
     существо
    0.41
    被称为
    0.41
     تھے
    0.41
     problème
    0.41
    POSITIVE LOGITS
    ג
    0.54
    vidas
    0.47
    లు
    0.46
     Regis
    0.45
     disputed
    0.44
     Tari
    0.44
    فات
    0.44
    PEZ
    0.44
    تاز
    0.43
    Auch
    0.42
    Activations Density 0.001%

    No Known Activations