© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15440
    Prev
    Next
    INDEX
    Explanations

    general words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    ـ
    0.51
    ”。
    0.50
    ـــ
    0.50
    ’।
    0.49
    ــــــــ
    0.49
    ــــ
    0.47
    ”、“
    0.46
    <0xE0>
    0.45
    ــ
    0.45
    '।
    0.44
    POSITIVE LOGITS
     some
    0.53
     Olm
    0.49
    inya
    0.48
     Fletcher
    0.47
     even
    0.46
     actively
    0.46
    ikes
    0.46
    ions
    0.45
     Ross
    0.45
    ersen
    0.45
    Activations Density 0.054%

    No Known Activations