© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 7844
    Prev
    Next
    INDEX
    Explanations

    defining words or slang

    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_all/layer_41_width_262k_l0_big
    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
     geschikt
    0.55
    ំន
    0.53
     زیرمه
    0.52
    近似
    0.52
     requisito
    0.51
     เหมาะ
    0.50
     circuito
    0.50
    摡
    0.50
     മിക
    0.49
     segmento
    0.49
    POSITIVE LOGITS
     noun
    0.91
     adjective
    0.91
     adjectives
    0.80
     Oxford
    0.77
    Noun
    0.75
     slang
    0.75
     Merriam
    0.75
     Dictionary
    0.73
     nouns
    0.69
     verb
    0.69
    Activations Density 0.023%

    No Known Activations