© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3383
    Prev
    Next
    INDEX
    Explanations

    code instructions ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    ayog
    1.26
     segmental
    1.21
    }^{*}-
    1.20
    ูนย์
    1.15
     Bina
    1.14
     Kähler
    1.13
    ^{*}(
    1.11
     Deutscher
    1.11
    zol
    1.10
    ฐ
    1.10
    POSITIVE LOGITS
     Mc
    3.21
    Mc
    2.93
     mc
    2.35
     McA
    2.19
     McN
    2.00
    mc
    1.94
     McEl
    1.93
     McD
    1.92
     McC
    1.83
     McM
    1.78
    Activations Density 0.031%

    No Known Activations