© 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. 40-GEMMASCOPE-2-RES-262K
    7. 8569
    Prev
    Next
    INDEX
    Explanations

    names followed by specific words

    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
    ানির
    0.27
     utopian
    0.25
    ೈ
    0.25
     Jawaharlal
    0.25
    yuan
    0.24
     Klinefelter
    0.24
     Muhammadu
    0.24
     Zentral
    0.23
     Juno
    0.23
    IVAL
    0.23
    POSITIVE LOGITS
    IdleSync
    0.35
    legas
    0.30
     एखा
    0.29
     perquè
    0.29
     مذکور
    0.29
    狧
    0.28
     પોતાની
    0.28
    rzez
    0.28
     परन्तु
    0.28
    gré
    0.27
    Activations Density 0.098%

    No Known Activations