© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12454
    Prev
    Next
    INDEX
    Explanations

    tell me

    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
    -
    1.30
     outside
    1.18
     external
    1.13
    ’
    1.06
     Outside
    1.05
     or
    1.04
     overseas
    1.00
     External
    0.99
    ®
    0.99
    /
    0.98
    POSITIVE LOGITS
    𒊕
    1.57
    㶲
    1.56
    <unused1606>
    1.55
    𒋀
    1.55
    <unused1293>
    1.54
    utilizzo
    1.54
    <unused1592>
    1.54
    <unused1490>
    1.53
    <unused1499>
    1.53
    <unused1312>
    1.52
    Activations Density 0.024%

    No Known Activations