© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    extensions, interrupts, conflicts

    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
    丈
    2.27
    igos
    2.12
    istic
    2.07
    ifiably
    1.88
    ಿಗ
    1.86
    垩
    1.85
    ιχ
    1.80
     strolled
    1.78
    ize
    1.77
    භ
    1.74
    POSITIVE LOGITS
    sectional
    2.54
    很有
    2.43
    amazonaws
    2.40
     confl
    2.31
     jurisdictional
    2.30
    новения
    2.29
    nown
    2.28
    нию
    2.25
    uée
    2.21
    <unused178>
    2.20
    Activations Density 0.146%

    No Known Activations