© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4648
    Prev
    Next
    INDEX
    Explanations

    free cost and availability

    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_13_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
     กับ
    1.30
     는
    1.20
     보면
    1.17
    ،
    1.17
    、
    1.16
     :=
    1.13
    보면
    1.12
     是
    1.10
     를
    1.07
    ,{\
    1.03
    POSITIVE LOGITS
    》。
    0.98
     endogenous
    0.97
     exogenous
    0.95
     honorable
    0.95
     spirito
    0.92
     afect
    0.91
    ”.
    0.90
     bienestar
    0.90
    ”。
    0.90
    ”।
    0.89
    Activations Density 0.049%

    No Known Activations