© 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. 161971
    Prev
    Next
    INDEX
    Explanations

    understanding that

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

    based on specification

    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
     in
    0.58
     ۵
    0.55
     ۸
    0.52
     it
    0.52
     e
    0.51
    ৭
    0.50
     de
    0.50
     s
    0.49
    ５
    0.49
     zonal
    0.48
    POSITIVE LOGITS
    ബരിമല
    0.47
    cw
    0.46
     basé
    0.45
    asko
    0.44
     ন্যায
    0.44
    に基づいて
    0.43
    ोटेन
    0.43
    fections
    0.42
    σκε
    0.42
    kowicz
    0.42
    Activations Density 0.000%

    No Known Activations