© 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. 3433
    Prev
    Next
    INDEX
    Explanations

    dawn

    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
    kai
    2.62
    lle
    2.57
    credible
    2.56
    了
    2.49
    сть
    2.48
     становништво
    2.44
    mallow
    2.41
    kende
    2.40
    ところが
    2.39
    ಝ
    2.34
    POSITIVE LOGITS
    ി
    2.41
     Far
    2.32
     anzi
    2.25
     tak
    2.24
    en
    2.21
    ISTR
    2.19
    しくは
    2.18
    ತಿ
    2.17
    Far
    2.13
    ormap
    2.12
    Activations Density 0.000%

    No Known Activations