© 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. 11653
    Prev
    Next
    INDEX
    Explanations

    muscular descriptions

    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
    います
    2.90
    了
    2.47
    gı
    2.44
    ted
    2.37
    tss
    2.34
    ヰ
    2.31
    də
    2.28
    lero
    2.25
    น้ำ
    2.25
    alámb
    2.24
    POSITIVE LOGITS
    स्पद
    1.98
    jak
    1.92
    "।
    1.76
    ৫
    1.76
    fine
    1.75
    odd
    1.67
    jr
    1.65
    ity
    1.64
    }",
    1.63
    eteen
    1.62
    Activations Density 0.008%

    No Known Activations