© 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. 6028
    Prev
    Next
    INDEX
    Explanations

    set to 2035

    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
     tenants
    0.37
     सप्टेंबर
    0.37
     several
    0.36
    เซีย
    0.35
     estimated
    0.34
     IANS
    0.34
    ження
    0.34
     "****
    0.34
     ino
    0.34
     mediators
    0.34
    POSITIVE LOGITS
    dst
    0.39
    uidor
    0.39
    ahren
    0.37
    ALT
    0.36
     Austral
    0.36
    mak
    0.36
    iban
    0.35
    plt
    0.35
    STD
    0.35
     പരിശ
    0.34
    Activations Density 0.001%

    No Known Activations