© 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. 227575
    Prev
    Next
    INDEX
    Explanations

    specific preceding context

    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
    :
    0.79
    (
    0.75
    .
    0.66
     P
    0.62
     St
    0.60
    /
    0.57
     K
    0.56
      
    0.56
     B
    0.55
     R
    0.55
    POSITIVE LOGITS
    ഭ്യാസ
    0.54
    elwv
    0.50
    攙
    0.49
    <unused9>
    0.49
     divaricatis
    0.49
     indivíduos
    0.49
     posticis
    0.49
     அக்க
    0.49
     আয়নের
    0.49
     svojih
    0.49
    Activations Density 0.000%

    No Known Activations