© 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. 107125
    Prev
    Next
    INDEX
    Explanations

    steel, svg, unix, apply

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

    qualities, names, and information

    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
    悩
    0.51
    ナ
    0.50
    ザ
    0.48
    ς
    0.46
    watts
    0.46
    щё
    0.45
    ரா
    0.45
    糁
    0.45
    呟
    0.44
    upo
    0.43
    POSITIVE LOGITS
     পরিণত
    0.52
     छोड़ा
    0.50
    cesz
    0.48
     foregoing
    0.47
    ,”
    0.46
     Enable
    0.46
     준
    0.45
    azuje
    0.45
     Carton
    0.45
     decentral
    0.45
    Activations Density 0.000%

    No Known Activations