© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11430
    Prev
    Next
    INDEX
    Explanations

    KE and selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    बंध
    1.98
    ेक्षित
    1.76
    =")"
    1.69
     Decline
    1.65
     أغ
    1.64
    ﻐ
    1.64
     Pog
    1.64
    얌
    1.63
     definitive
    1.60
    Integrante
    1.60
    POSITIVE LOGITS
    observ
    1.78
    eid
    1.73
    ourses
    1.72
    都有
    1.70
    idespread
    1.64
    simpl
    1.58
    obs
    1.58
    rapers
    1.56
    যজ্ঞ
    1.56
    прочем
    1.55
    Activations Density 0.000%

    No Known Activations