© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7997
    Prev
    Next
    INDEX
    Explanations

    There is pattern in lists

    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_22_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
    uí
    1.08
    owanym
    1.07
     thankfully
    1.03
    Ⅽ
    0.98
     conjunct
    0.98
     frank
    0.98
     extremity
    0.98
    变得
    0.97
    cmap
    0.97
    ☬
    0.96
    POSITIVE LOGITS
     consultez
    0.90
     müşteri
    0.85
    γρά
    0.84
    rž
    0.81
    作り
    0.79
     نگه
    0.76
     результатов
    0.76
     pajak
    0.74
    殺
    0.72
    rends
    0.72
    Activations Density 0.000%

    No Known Activations