© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    offering choices

    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
    ا۔
    2.26
    ا
    2.07
    pont
    1.89
    एफआई
    1.82
     دھو
    1.82
    glieder
    1.78
    ೆ
    1.77
    tak
    1.76
     cittam
    1.72
    幟
    1.70
    POSITIVE LOGITS
     Baby
    1.92
     Romance
    1.85
    YAN
    1.84
    Baby
    1.82
     Solid
    1.74
    Kitty
    1.71
    τζ
    1.67
     staples
    1.65
     Mois
    1.63
    Carter
    1.63
    Activations Density 0.043%

    No Known Activations