© 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. 97741
    Prev
    Next
    INDEX
    Explanations

    served you

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

    influence on market

    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
    4
    0.64
    5
    0.63
    map
    0.62
    3
    0.59
    2
    0.58
    alt
    0.57
    well
    0.57
    O
    0.57
    6
    0.56
    પ
    0.56
    POSITIVE LOGITS
     fibrils
    0.61
     tarses
    0.54
     atletas
    0.54
     hız
    0.54
     evaluated
    0.53
     egz
    0.52
     kadın
    0.52
     ovar
    0.52
     spasms
    0.52
     eliminated
    0.50
    Activations Density 0.000%

    No Known Activations