© 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. 11464
    Prev
    Next
    INDEX
    Explanations

    stand

    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
    ोत्तम
    3.10
    ষম
    3.03
    okhttp
    3.00
    ήμε
    2.88
     escaped
    2.75
    ratulations
    2.74
    handlebars
    2.65
    垩
    2.64
    做到
    2.60
    ජ
    2.58
    POSITIVE LOGITS
    ১
    2.40
     سك
    2.32
    rock
    2.31
    ★★
    2.26
    ပိုင်း
    2.20
    িয়া
    2.18
    ვ
    2.17
    まち
    2.17
    ゆっくり
    2.16
     Nub
    2.16
    Activations Density 0.107%

    No Known Activations