© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    trevor project support

    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
    መ
    1.68
    inum
    1.66
     cialis
    1.65
     zenith
    1.63
     सन्
    1.62
    ূ
    1.58
    нё
    1.57
     ail
    1.56
     ILL
    1.54
    isimple
    1.53
    POSITIVE LOGITS
     контроль
    2.04
    ғы
    2.04
    pieces
    2.04
    깥
    1.98
     disponibles
    1.97
    ριο
    1.95
     movers
    1.94
    Segments
    1.94
     isolates
    1.94
    δα
    1.93
    Activations Density 0.130%

    No Known Activations