© 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. 36338
    Prev
    Next
    INDEX
    Explanations

    project focuses, Junior Young, among other

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

    handle a

    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
    le
    0.58
    ل
    0.54
    oj
    0.50
    kennt
    0.50
    por
    0.49
    pl
    0.48
    reinforced
    0.47
    پن
    0.47
    3
    0.47
    л
    0.47
    POSITIVE LOGITS
    াহারের
    0.50
     Karite
    0.46
     Searle
    0.46
     Plenty
    0.46
    见面
    0.46
     आल्या
    0.44
    mathbb
    0.44
     সারি
    0.44
     Tricks
    0.43
     Figma
    0.43
    Activations Density 0.000%

    No Known Activations