© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13083
    Prev
    Next
    INDEX
    Explanations

    javascript `const`s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ς
    1.07
    theless
    1.02
    s
    1.02
     жив
    1.00
    𝐬
    0.95
     ọ
    0.93
     către
    0.89
    ्स
    0.89
    𝐩
    0.88
    ↵↵
    0.88
    POSITIVE LOGITS
    larda
    1.37
    на
    1.28
    ان
    1.20
    an
    1.19
    ar
    1.12
    at
    1.10
    Послед
    1.10
    <blockquote>
    1.08
    ת
    1.08
    lardan
    1.00
    Activations Density 1.460%

    No Known Activations