© 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. 131826
    Prev
    Next
    INDEX
    Explanations

    co-instructional activities

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

    update, data, route, status

    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
    iguiente
    0.50
     تقریبا
    0.48
    bottlecap
    0.47
    袷
    0.47
    それぞれ
    0.46
    ждый
    0.46
    ۩
    0.46
    ிலிருந்து
    0.45
    ایش
    0.44
     Marissa
    0.44
    POSITIVE LOGITS
    ToDo
    0.49
    todo
    0.47
    genommen
    0.46
    ἥ
    0.45
    dd
    0.44
    getVisibility
    0.44
    rem
    0.43
    small
    0.43
    core
    0.42
    checkFor
    0.42
    Activations Density 0.000%

    No Known Activations