© 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. 53465
    Prev
    Next
    INDEX
    Explanations

    It's

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

    gathering tinder

    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
    ROAD
    0.52
    Iterator
    0.49
    FACTOR
    0.48
     adjoining
    0.47
    GENER
    0.46
    &(
    0.46
    Athlete
    0.46
    <0x80>
    0.46
    UNDO
    0.46
     mollus
    0.45
    POSITIVE LOGITS
     देसी
    0.52
     Provision
    0.48
     zeker
    0.48
     टी
    0.45
     Samu
    0.44
    бели
    0.43
     টি
    0.42
    做好
    0.41
     Inbetriebnahme
    0.41
    何
    0.41
    Activations Density 0.000%

    No Known Activations