© 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. 174764
    Prev
    Next
    INDEX
    Explanations

    connecting words

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

    deep states and stages appearing

    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
     incorrect
    0.51
     inaccurate
    0.50
    0
    0.49
     associating
    0.48
     excurs
    0.47
     edition
    0.46
    (
    0.46
    1
    0.45
     REPLACE
    0.45
     updates
    0.45
    POSITIVE LOGITS
    分辨率
    0.46
     Russland
    0.45
     Nonlinear
    0.45
    등급
    0.44
    书法
    0.44
    MSFontService
    0.43
     ℝ
    0.42
    芓
    0.42
     পৃথিবীর
    0.42
    ळख
    0.41
    Activations Density 0.000%

    No Known Activations