© 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. 105112
    Prev
    Next
    INDEX
    Explanations

    meals, experience, games, teachers, radial

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

    robotic, wander, ingredients, destination

    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
     catt
    0.53
     flaky
    0.49
     luna
    0.48
     #[
    0.48
     graines
    0.47
    թ
    0.47
     mus
    0.46
     twenty
    0.46
     hoof
    0.46
     doc
    0.46
    POSITIVE LOGITS
    rah
    0.53
    enciais
    0.49
    糍
    0.48
    habitude
    0.48
    rahman
    0.46
    antra
    0.45
    auté
    0.45
    setName
    0.44
    felder
    0.44
    რა
    0.44
    Activations Density 0.000%

    No Known Activations