© 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. 251755
    Prev
    Next
    INDEX
    Explanations

    noun phrases and verb phrases

    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
     camb
    0.52
     académicos
    0.52
     afectada
    0.50
    ب
    0.49
     G
    0.49
    netje
    0.49
     Racine
    0.48
     académ
    0.48
     Saito
    0.47
     ambas
    0.47
    POSITIVE LOGITS
    Callories
    0.45
    之間
    0.44
    Requires
    0.43
    Hooks
    0.43
    ព័ន្ធ
    0.42
    LaunchScheme
    0.41
    瑉
    0.41
    %}
    0.41
    dome
    0.41
    $^
    0.40
    Activations Density 0.002%

    No Known Activations