© 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. 25342
    Prev
    Next
    INDEX
    Explanations

    language and its outcomes

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

    internet and tools

    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
    rm
    0.57
    л
    0.48
    ре
    0.46
     examiners
    0.46
     gob
    0.45
    ampang
    0.45
    ire
    0.44
    Глав
    0.44
    ゲ
    0.44
    ку
    0.44
    POSITIVE LOGITS
    ऊदी
    0.52
     Einwilligung
    0.47
     variabel
    0.47
     मसल्स
    0.46
     Metabolism
    0.46
    Wells
    0.45
    不然
    0.43
     Continuando
    0.43
     hvilket
    0.43
     ब्रेस्ट
    0.43
    Activations Density 0.000%

    No Known Activations