© 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. 8609
    Prev
    Next
    INDEX
    Explanations

    FT followed by AT

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

    server software configuration

    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
    Pupp
    0.52
     workaround
    0.52
    T
    0.50
    l
    0.49
     surprise
    0.49
    v
    0.48
    r
    0.48
    再加上
    0.47
    ‪
    0.47
    f
    0.46
    POSITIVE LOGITS
    䚺
    0.46
     മുൻ
    0.46
    subseteq
    0.45
    船舶
    0.44
    क्यूमेंट
    0.43
    ൽപ്പന
    0.43
     slits
    0.42
     pSig
    0.42
     dikdört
    0.42
     Öl
    0.42
    Activations Density 0.000%

    No Known Activations