© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2954
    Prev
    Next
    INDEX
    Explanations

    technical phrases and notations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    resel
    0.64
    änglich
    0.63
     sold
    0.63
    एसआई
    0.61
     SI
    0.61
     ఇ
    0.60
     PSE
    0.60
     frame
    0.59
    솔
    0.59
     soziale
    0.58
    POSITIVE LOGITS
     voci
    0.70
     voce
    0.69
    voc
    0.65
    ოფ
    0.64
    v
    0.64
    acil
    0.62
     Cooke
    0.62
     لام
    0.61
     v
    0.61
    ክል
    0.61
    Activations Density 0.197%

    No Known Activations