© 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. 130859
    Prev
    Next
    INDEX
    Explanations

    words often following prepositions

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

    contaminated or spiritual or single copy

    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
     réessayer
    0.46
     huid
    0.45
     可愛
    0.44
     mou
    0.44
     exponents
    0.44
     назнача
    0.44
    <unused346>
    0.44
     lauf
    0.43
     แอป
    0.43
     haszn
    0.42
    POSITIVE LOGITS
    燃料
    0.48
     पेट्रोल
    0.42
    LEGISLATIVE
    0.42
    ევს
    0.41
    LETTER
    0.41
    忆
    0.41
     दैन
    0.40
    TOK
    0.40
    데일리
    0.40
     rohk
    0.40
    Activations Density 0.000%

    No Known Activations