© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    vulnerable, effective, or ineffective

    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
    eea
    2.44
    ActionBar
    2.42
    лектро
    2.39
     اور
    2.33
    یاز
    2.31
    ﻕ
    2.29
    illier
    2.28
    таж
    2.25
    ላይ
    2.24
    etière
    2.24
    POSITIVE LOGITS
    utenants
    3.39
    र
    3.34
    ers
    2.89
    <bos>
    2.88
    managed
    2.72
    年モデル
    2.71
    chtenstein
    2.70
    archical
    2.69
    haps
    2.67
     sıra
    2.48
    Activations Density 0.100%

    No Known Activations