© 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. 106207
    Prev
    Next
    INDEX
    Explanations

    offers, pages, visit, locations

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

    country, nation, summer, season

    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
    <0x0D>
    0.53
     Rude
    0.47
     universe
    0.47
     fathom
    0.46
     comprehend
    0.45
    čí
    0.44
     verhaal
    0.43
     meantime
    0.43
    წერ
    0.43
    া
    0.43
    POSITIVE LOGITS
    increases
    0.55
    YK
    0.47
    ೇವ
    0.47
     όταν
    0.47
    integrated
    0.45
     enseñanzas
    0.45
     operativos
    0.45
    鱔
    0.45
    ANGO
    0.45
    បន្ទ
    0.44
    Activations Density 0.000%

    No Known Activations