© 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. 61582
    Prev
    Next
    INDEX
    Explanations

    determiner/preposition followed by noun

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

    batch effects, attraction, style, gas, tickets, Elo

    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
     async
    0.50
     꾸
    0.48
    ходите
    0.46
     aggravated
    0.44
     offset
    0.44
     upset
    0.43
     worsening
    0.42
     damper
    0.42
    iduría
    0.42
     dampen
    0.42
    POSITIVE LOGITS
    サービスの
    0.56
    在
    0.50
    كتب
    0.50
    質
    0.49
    وس
    0.49
    他的
    0.48
    Alberto
    0.48
    選項
    0.48
    Packages
    0.48
    聲
    0.48
    Activations Density 0.000%

    No Known Activations