© 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. 44581
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    deployment and integration models

    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
     sovereignty
    0.43
     két
    0.43
    ពួកគេ
    0.42
     ethic
    0.41
    <0xA2>
    0.41
    フォー
    0.41
     Bé
    0.41
     conglomerate
    0.40
     Bá
    0.40
    港
    0.40
    POSITIVE LOGITS
    platte
    0.52
    auj
    0.52
    simply
    0.50
     scegli
    0.46
    리의
    0.46
     sonst
    0.46
    dirs
    0.46
    Dip
    0.45
    πους
    0.45
    simpl
    0.45
    Activations Density 0.001%

    No Known Activations