© 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. 142987
    Prev
    Next
    INDEX
    Explanations

    you want

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

    perform many

    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
     Also
    0.48
    Through
    0.46
     ChatGPT
    0.46
     PUBG
    0.45
     Williamsburg
    0.45
     ACHIE
    0.45
    ዊ
    0.45
     Through
    0.45
     PUBL
    0.44
     GAO
    0.44
    POSITIVE LOGITS
     PDPN
    0.45
    ophenyl
    0.43
    াবা
    0.42
    痘
    0.42
     nervous
    0.42
    差別
    0.39
     satunya
    0.38
    rightbar
    0.38
     alarm
    0.37
    reflectionMap
    0.37
    Activations Density 0.000%

    No Known Activations