© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    general shifts in what's accepted

    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
    ід
    0.56
     нужно
    0.54
     สามารถ
    0.51
    Precision
    0.51
    Accuracy
    0.50
    榨
    0.49
     작업
    0.48
    Geometry
    0.47
     Accuracy
    0.47
    汤
    0.46
    POSITIVE LOGITS
     apoyo
    0.79
     apoyar
    0.75
     recognizes
    0.73
     willingness
    0.72
     consens
    0.72
     endorsing
    0.72
     attitudes
    0.71
     ủng
    0.71
     abhor
    0.70
     beliefs
    0.69
    Activations Density 0.207%

    No Known Activations