© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14275
    Prev
    Next
    INDEX
    Explanations

    function encapsulation for reusability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.84
    னின்
    0.71
     //
    0.68
    ذة
    0.65
    ίδα
    0.65
    :
    0.64
     primitive
    0.63
    வின்
    0.61
     خوب
    0.59
     classique
    0.59
    POSITIVE LOGITS
    圿
    1.03
    cable
    0.96
    ٸ
    0.95
    挖
    0.94
     Realtors
    0.93
    <unused988>
    0.93
    夰
    0.93
     harboring
    0.91
     Congr
    0.90
    rake
    0.90
    Activations Density 0.051%

    No Known Activations