© 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. 12471
    Prev
    Next
    INDEX
    Explanations

    requirements unmet or conditions to be met

    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
    탉
    1.96
    وظ
    1.92
    大多
    1.89
     equipes
    1.86
    ری
    1.86
    一名
    1.84
    ের
    1.83
     Facing
    1.82
    面临
    1.80
    AddModelError
    1.79
    POSITIVE LOGITS
    ikan
    1.51
    ivative
    1.37
     defibr
    1.37
     ähm
    1.36
    ifu
    1.33
     whatsoever
    1.33
    ຟ
    1.32
     spec
    1.31
    quir
    1.31
    目で
    1.30
    Activations Density 0.042%

    No Known Activations