© 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. 179111
    Prev
    Next
    INDEX
    Explanations

    online ordering

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

    jokes targeting groups

    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
    си
    0.50
    ре
    0.49
     Kr
    0.47
    чне
    0.47
     adopter
    0.47
     imperfections
    0.46
    <0x0D>
    0.46
    xa
    0.45
    л
    0.44
    ค
    0.44
    POSITIVE LOGITS
     osim
    0.48
     겸
    0.48
    켰
    0.47
    drugs
    0.46
     مول
    0.42
     carcinogenesis
    0.42
     اکاؤن
    0.42
    ڈین
    0.42
     Моло
    0.42
     heparin
    0.42
    Activations Density 0.000%

    No Known Activations