© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13801
    Prev
    Next
    INDEX
    Explanations

    csp, llama, strlen

    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
     १६
    1.42
    לה
    1.40
    undu
    1.40
    IPE
    1.39
    ﻔ
    1.36
    дето
    1.35
    ุก
    1.33
     वेरिएबल
    1.30
     energetic
    1.29
    𝗨
    1.28
    POSITIVE LOGITS
    š
    1.63
     révolution
    1.56
    的東西
    1.53
    (
    1.47
    總統
    1.39
     gomme
    1.36
     komputer
    1.35
    stown
    1.35
    Button
    1.35
     navigateur
    1.34
    Activations Density 0.002%

    No Known Activations