© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14067
    Prev
    Next
    INDEX
    Explanations

    Chapter title

    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_13_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
     Tune
    1.97
    ಖ್ಯ
    1.86
    Powers
    1.84
     $*
    1.84
    અ
    1.83
     thuế
    1.82
     ـ
    1.78
     petitioner
    1.76
     Ugar
    1.76
    hammad
    1.75
    POSITIVE LOGITS
    lab
    1.48
    d
    1.39
     рассчита
    1.35
    ‐
    1.33
     зон
    1.33
    larda
    1.26
    nip
    1.26
     reinforcement
    1.24
    ल्याण
    1.23
    lar
    1.23
    Activations Density 0.000%

    No Known Activations