© 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. 12785
    Prev
    Next
    INDEX
    Explanations

    sale, intestazione

    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
    u
    3.03
    off
    2.63
    ेडकर
    2.49
    offs
    2.47
    parent
    2.47
    Â
    2.46
    ாலிக
    2.43
    odds
    2.42
    破損
    2.40
    EditorGUI
    2.39
    POSITIVE LOGITS
    ل
    2.31
    ↵↵↵↵↵↵↵↵↵
    2.25
    zinho
    2.22
    istik
    2.21
    حه
    2.16
     例文帳に追加
    2.12
    忑
    2.10
    ↵↵↵↵↵↵↵↵↵↵↵
    2.07
    zied
    2.04
    STRO
    2.04
    Activations Density 0.010%

    No Known Activations