© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14266
    Prev
    Next
    INDEX
    Explanations

    official, networking, tool, lower

    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_13_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
    s
    1.17
    阻
    1.16
    ุป
    1.12
     性
    1.09
    тным
    1.07
    rise
    1.07
    ্
    1.06
    substring
    1.05
    тности
    1.05
    гү
    1.05
    POSITIVE LOGITS
    ﻦ
    1.55
    SuppressWarnings
    1.51
    ouwd
    1.37
    alling
    1.35
     එව
    1.35
    Cuánto
    1.33
    𝘂
    1.31
    startTimestamp
    1.31
    Paxos
    1.30
    èlement
    1.28
    Activations Density 0.000%

    No Known Activations