© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34500
    Prev
    Next
    INDEX
    Explanations

    numbers and credit hours

    np_acts-logits-general · gemini-2.5-flash-lite

    health and social groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وقف
    0.57
    职责
    0.52
    宄
    0.52
    OnUiThread
    0.51
    の説明
    0.51
    纂
    0.49
     كبير
    0.48
    的技术
    0.48
     Terence
    0.48
    酊
    0.47
    POSITIVE LOGITS
    i
    0.56
     and
    0.53
     increase
    0.48
    female
    0.48
     incisions
    0.47
     increases
    0.47
     ISA
    0.47
     increments
    0.46
    ennies
    0.46
     expenditures
    0.45
    Activations Density 0.000%

    No Known Activations