© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1622
    Prev
    Next
    INDEX
    Explanations

    Sound quality and accountability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Reason
    0.97
     Bureau
    0.96
    nationality
    0.89
    Perf
    0.87
    컹
    0.85
     pints
    0.84
    irk
    0.84
     birl
    0.84
     Pho
    0.83
     Perf
    0.83
    POSITIVE LOGITS
    igi
    0.86
     Joshua
    0.85
     oscillatory
    0.81
     orbit
    0.81
    吉
    0.80
    Monte
    0.80
    Jessica
    0.79
     MCC
    0.79
     Jessica
    0.78
    shima
    0.78
    Activations Density 0.575%

    No Known Activations