© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12407
    Prev
    Next
    INDEX
    Explanations

    local API endpoints

    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
    Baca
    2.15
    ⬯
    2.13
    unud
    2.10
    𝐘
    2.09
     دهد
    2.09
    Signing
    2.05
    ﻉ
    2.00
    Zitat
    1.99
    तोष
    1.98
    M
    1.98
    POSITIVE LOGITS
    lexer
    1.97
    urname
    1.97
    凸
    1.85
    果た
    1.84
    詡
    1.79
    ेक्षित
    1.78
     স্বীকার
    1.75
     armchair
    1.72
    dote
    1.71
    注入
    1.71
    Activations Density 0.001%

    No Known Activations