© 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. 24929
    Prev
    Next
    INDEX
    Explanations

    minor source, respectively, tires, soak and sprout, leading a campaign, drivers

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

    Platforms Supported

    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
     resto
    0.47
    писание
    0.44
    mex
    0.41
    レシピ
    0.40
     극
    0.40
    銀行
    0.40
     મહિ
    0.40
     ケ
    0.39
    MEX
    0.38
     FMT
    0.38
    POSITIVE LOGITS
    每个人
    0.43
    ārt
    0.42
     Crock
    0.41
    একটা
    0.41
     Weinstein
    0.40
     සා
    0.40
    preventDefault
    0.39
     लागेल
    0.39
    someone
    0.39
    $/.
    0.39
    Activations Density 0.000%

    No Known Activations