© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13033
    Prev
    Next
    INDEX
    Explanations

    say punctuation

    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
     –
    1.71
     —
    1.62
     --
    1.37
     -
    1.13
    !”
    1.13
     –,
    1.13
     ـ
    1.12
     aka
    1.08
    —“
    1.08
    —
    1.05
    POSITIVE LOGITS
    แม้
    0.72
     meskipun
    0.71
     walaupun
    0.70
     Meskipun
    0.66
    即使
    0.64
     ITable
    0.64
     Although
    0.62
     möglicherweise
    0.60
    尽管
    0.60
    Notwithstanding
    0.59
    Activations Density 0.037%

    No Known Activations