© 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. 25855
    Prev
    Next
    INDEX
    Explanations

    seeking confirmation

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

    tag questions

    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
     ଶ
    0.48
    ,),
    0.44
    oclip
    0.42
    ,...,
    0.40
     облі
    0.39
     трансформа
    0.39
     datth
    0.39
     ση
    0.39
     шести
    0.39
    ,»
    0.38
    POSITIVE LOGITS
    ?
    0.68
    ？
    0.68
    ؟
    0.66
    ?/
    0.58
    ?!
    0.56
    ?..
    0.56
    ?(
    0.54
    ?-
    0.54
     그죠
    0.51
    ?:
    0.50
    Activations Density 0.027%

    No Known Activations