© 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. 31-GEMMASCOPE-2-RES-262K
    7. 40695
    Prev
    Next
    INDEX
    Explanations

    acroposthion, researcher, highlight

    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_31_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
    hla
    0.47
    ವಾರು
    0.47
    踐
    0.46
     imputation
    0.45
     immisc
    0.44
    '=>$
    0.44
     imposes
    0.44
    მასრულ
    0.43
    ôs
    0.43
    栥
    0.43
    POSITIVE LOGITS
     May
    0.50
     Today
    0.50
    ද්ධ
    0.49
    onal
    0.48
    This
    0.47
    on
    0.46
    one
    0.45
    Today
    0.45
    Todd
    0.44
     Todd
    0.44
    Activations Density 0.000%

    No Known Activations