© 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. 154575
    Prev
    Next
    INDEX
    Explanations

    tea towels

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

    prepositions or conjunctions introducing context

    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
    vano
    0.50
    opos
    0.50
    ampton
    0.48
    inov
    0.47
    princ
    0.45
    battle
    0.45
    ’
    0.44
     Kasper
    0.44
     ín
    0.44
    translations
    0.44
    POSITIVE LOGITS
    卸
    0.50
    抽
    0.48
     Anime
    0.48
    騰
    0.48
    瞬间
    0.47
    淘
    0.46
     Texture
    0.45
     (>
    0.44
     Convolution
    0.44
     Laundry
    0.44
    Activations Density 0.001%

    No Known Activations