© 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. 193656
    Prev
    Next
    INDEX
    Explanations

    Business Reviews

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

    driven by

    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
    𝘰
    0.53
    𝘮
    0.48
     Einführung
    0.47
    ｯ
    0.47
     títulos
    0.46
    amı
    0.46
    𝙝
    0.46
     micró
    0.46
    PROGRAM
    0.46
    ک
    0.45
    POSITIVE LOGITS
    adz
    0.51
    Lena
    0.44
    ão
    0.44
    =
    0.44
    ,»
    0.44
    ,”
    0.43
     Selatan
    0.43
    getLocal
    0.43
     src
    0.41
    imental
    0.41
    Activations Density 0.001%

    No Known Activations