© 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. 61659
    Prev
    Next
    INDEX
    Explanations

    biological age, lithiation

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

    contrasting conjunctions

    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
    ำ
    0.44
    に入る
    0.43
    ymp
    0.43
     господар
    0.43
    ्तर
    0.42
     admirer
    0.42
    нцикло
    0.41
    том
    0.41
    𝘂
    0.41
     घरे
    0.40
    POSITIVE LOGITS
     الشي
    0.48
     discut
    0.44
    فيق
    0.44
    ForegroundColor
    0.44
    في
    0.43
    可行
    0.43
     Ka
    0.43
     suficientes
    0.43
     veut
    0.42
     substitu
    0.42
    Activations Density 0.000%

    No Known Activations