© 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. 17955
    Prev
    Next
    INDEX
    Explanations

    positive evaluations and guidance

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

    Deity names and pronouns

    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
     amending
    0.43
    $
    0.36
     ګ
    0.35
     /$
    0.35
     accounts
    0.35
    $`
    0.35
     amendments
    0.34
     thiên
    0.34
     ư
    0.34
    새
    0.34
    POSITIVE LOGITS
     অথচ
    0.44
    idać
    0.43
    ieved
    0.41
    icitis
    0.40
     dioxide
    0.39
     Months
    0.39
     মাসের
    0.39
    ヶ月
    0.39
    odiac
    0.39
    emás
    0.39
    Activations Density 0.036%

    No Known Activations