© 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. 359
    Prev
    Next
    INDEX
    Explanations

    forum posts

    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
    [
    0.46
     guessing
    0.43
    adds
    0.42
    iqueness
    0.41
     uner
    0.40
     thickening
    0.40
     intriguing
    0.40
    )+'
    0.40
    relationships
    0.40
     reflect
    0.39
    POSITIVE LOGITS
     anciens
    0.49
     બદ
    0.48
     widows
    0.44
     públicas
    0.44
    PROCESS
    0.43
    Ｔ
    0.43
    남도
    0.43
     mesmas
    0.42
     निजात
    0.42
     Lyrics
    0.42
    Activations Density 0.000%

    No Known Activations