© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    study guides and papers

    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
    اته
    0.48
    ط
    0.41
    !,
    0.41
    龍
    0.40
     Purposes
    0.40
     Results
    0.39
    ↵
    0.39
    IL
    0.38
    ار
    0.37
     Surround
    0.37
    POSITIVE LOGITS
     crumpled
    0.59
     outraged
    0.49
     hii
    0.49
     incriminating
    0.49
     WordPerfect
    0.48
     scarring
    0.48
     spindles
    0.48
     گرفتار
    0.48
     अवे
    0.47
     fattori
    0.47
    Activations Density 0.000%

    No Known Activations