© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 133481
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases or compound nouns

    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_40_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
    畀
    0.43
     crypto
    0.41
     consegna
    0.40
     algebras
    0.38
    stens
    0.38
    ربون
    0.37
     Algebras
    0.37
    crypto
    0.37
     parum
    0.36
     maxY
    0.36
    POSITIVE LOGITS
    Nam
    0.43
    Raven
    0.39
    [-
    0.38
     हार्ड
    0.38
     heavy
    0.38
    <ul>
    0.38
     Namib
    0.37
     Raven
    0.37
     Nam
    0.37
    Lis
    0.37
    Activations Density 0.000%

    No Known Activations