© 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. 108065
    Prev
    Next
    INDEX
    Explanations

    comparing novel and movie

    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
    岘
    0.52
     المثلثيه
    0.50
     Developmental
    0.49
     COMPLEXES
    0.48
    ждены
    0.48
     مشرقی
    0.47
     вересня
    0.47
     Україн
    0.47
    外国
    0.46
    ლები
    0.46
    POSITIVE LOGITS
    !
    0.48
    arg
    0.46
    akses
    0.44
    adium
    0.44
     essays
    0.42
     recipe
    0.42
     pads
    0.41
    alo
    0.40
    とか
    0.39
     grape
    0.39
    Activations Density 0.006%

    No Known Activations