© 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. 12795
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts involving Shift

    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
    𝕤
    1.64
    fico
    1.53
    MANIFEST
    1.49
    𝘀
    1.47
    diagram
    1.47
    }{{
    1.47
    orie
    1.46
    榞
    1.46
    oman
    1.43
    藓
    1.42
    POSITIVE LOGITS
    NEXT
    1.48
     acrob
    1.35
     tấn
    1.31
     วิชา
    1.29
    тана
    1.29
     fouling
    1.28
     arcs
    1.27
     Baca
    1.26
     சுக
    1.26
    伏
    1.20
    Activations Density 0.042%

    No Known Activations