© 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. 202857
    Prev
    Next
    INDEX
    Explanations

    formal statements and follow-ups

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

    multilingual and specific details

    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
     запу
    0.53
    или
    0.50
     או
    0.48
    חות
    0.47
     impulsive
    0.46
     energ
    0.46
    לי
    0.45
    },\
    0.45
     wikiHow
    0.45
     כבר
    0.45
    POSITIVE LOGITS
    عه
    0.51
     complète
    0.49
     séparation
    0.48
     منصوبہ
    0.48
     gören
    0.46
    aisu
    0.45
    itada
    0.44
    arı
    0.44
     couvert
    0.43
     közö
    0.43
    Activations Density 0.000%

    No Known Activations