© 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. 32451
    Prev
    Next
    INDEX
    Explanations

    maintenance or operations

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

    stirring and mixing ingredients

    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
     Metallica
    0.47
     Brandon
    0.45
    实在是
    0.45
     Daniele
    0.45
     Dimitri
    0.44
     پایه
    0.44
     Dore
    0.44
    ഗ
    0.43
     Monique
    0.42
     Elisabeth
    0.42
    POSITIVE LOGITS
    積極
    0.44
     отделение
    0.44
    batross
    0.44
     diminuer
    0.43
    clearInterval
    0.43
    creatic
    0.41
     clearInterval
    0.40
    प्टेंबर
    0.40
    轄
    0.40
     политики
    0.39
    Activations Density 0.000%

    No Known Activations