© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    seeing, what, preferences, better, how

    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
    using
    0.43
    *
    0.42
     Ravi
    0.40
     Culture
    0.40
     Pairing
    0.39
     Insertion
    0.38
     Video
    0.38
    usc
    0.37
     Rift
    0.37
     R
    0.37
    POSITIVE LOGITS
    ніка
    0.47
     jednak
    0.44
     desider
    0.42
     espect
    0.41
     svært
    0.41
     niezwy
    0.41
     být
    0.41
    iędzy
    0.41
     karst
    0.41
     अत्यंत
    0.40
    Activations Density 0.001%

    No Known Activations