© 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. 175914
    Prev
    Next
    INDEX
    Explanations

    new crop

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

    unique sensations

    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
     caric
    0.54
     Jews
    0.53
     發
    0.48
     elér
    0.48
     دری
    0.47
     singers
    0.47
     vassals
    0.47
     တို့
    0.47
     odred
    0.46
     ■
    0.46
    POSITIVE LOGITS
    N
    0.64
    Services
    0.49
    Packaging
    0.49
    S
    0.49
    B
    0.48
    Hospital
    0.47
    K
    0.47
    Camping
    0.47
    Y
    0.47
    kt
    0.47
    Activations Density 0.000%

    No Known Activations