© 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. 131933
    Prev
    Next
    INDEX
    Explanations

    cross-stitch magazines

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

    ready to

    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
    verdad
    0.49
     tentacles
    0.46
    usuario
    0.46
    izen
    0.44
    ing
    0.44
    RefItem
    0.43
     ನೀಡ
    0.43
    ）
    0.43
    true
    0.42
    niji
    0.42
    POSITIVE LOGITS
     Ultrasound
    0.54
     Code
    0.53
     मैन
    0.53
     Nantes
    0.53
     Sơn
    0.51
     Nederland
    0.51
     Air
    0.50
     Iterate
    0.50
     Needle
    0.50
     Hand
    0.50
    Activations Density 0.000%

    No Known Activations