© 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. 80928
    Prev
    Next
    INDEX
    Explanations

    tilling widths; devout thought; precious metal

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

    words and associated punctuation

    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
    istics
    0.49
     силь
    0.44
    즘
    0.43
     disperse
    0.43
    ЕН
    0.43
     calculi
    0.43
     nguyện
    0.42
     objections
    0.42
     잠
    0.42
     eventual
    0.41
    POSITIVE LOGITS
     fidèle
    0.50
     എന്നാൽ
    0.49
     लेकिन
    0.46
     Presse
    0.45
     ऐतिहासिक
    0.45
     accompagnée
    0.44
     Chiara
    0.43
    োঁয়া
    0.43
     मजेदार
    0.43
     Madonna
    0.43
    Activations Density 0.001%

    No Known Activations