© 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. 196228
    Prev
    Next
    INDEX
    Explanations

    medical procedures

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

    foreign words and concepts

    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
     pouvant
    0.48
     puissent
    0.47
    ;
    0.46
    ):(
    0.46
    Zip
    0.45
    vens
    0.43
    となります
    0.43
    ્ષ
    0.42
    ]，
    0.42
    ):
    0.42
    POSITIVE LOGITS
     puree
    0.50
    美术
    0.47
     เหล
    0.46
    లూ
    0.46
     kaas
    0.46
     pulau
    0.46
     deel
    0.46
     Hulu
    0.46
     Warhol
    0.45
     देओल
    0.45
    Activations Density 0.000%

    No Known Activations