© 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. 106008
    Prev
    Next
    INDEX
    Explanations

    bands, blue plate, collectibles, cells

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

    direct alternatives

    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
    -
    0.45
     দৃ
    0.44
     Empor
    0.43
    '=
    0.42
     Kang
    0.42
    を有
    0.41
    riez
    0.40
    소가
    0.40
    vedo
    0.40
    manufacturing
    0.40
    POSITIVE LOGITS
     laaj
    0.48
     jednog
    0.46
    ദ
    0.46
     terve
    0.45
    дан
    0.45
    ром
    0.44
     comunit
    0.44
    ចាំ
    0.44
    ாடு
    0.43
    DOCKED
    0.43
    Activations Density 0.002%

    No Known Activations