© 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. 11762
    Prev
    Next
    INDEX
    Explanations

    assembly global declarations

    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
    ̯
    2.12
    ऑन
    1.98
    Electric
    1.97
     armazenamento
    1.96
    ❶
    1.95
    अनुसूचित
    1.94
    fyd
    1.89
    pendicular
    1.84
    ders
    1.83
     丿
    1.80
    POSITIVE LOGITS
    ű
    1.49
     blame
    1.46
     genocide
    1.46
     candle
    1.43
    푀
    1.42
     consec
    1.41
     tract
    1.41
     refute
    1.39
     personal
    1.38
     sabotage
    1.37
    Activations Density 0.130%

    No Known Activations