© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2936
    Prev
    Next
    INDEX
    Explanations

    specialized programming terms

    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_15_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
    ”:
    2.65
    ”,
    2.64
    ":
    2.58
    ,’”
    2.56
    ,”
    2.56
    ”.
    2.44
    ",
    2.42
    .",
    2.40
    .”
    2.38
    ,"
    2.38
    POSITIVE LOGITS
    </sup>
    2.46
    éments
    1.30
    ところが
    1.24
    그러나
    1.17
    ஆனால்
    1.14
     comulti
    1.14
     tarses
    1.14
    HARAD
    1.13
     entanto
    1.13
     rufis
    1.12
    Activations Density 0.010%

    No Known Activations