© 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-262K
    7. 145796
    Prev
    Next
    INDEX
    Explanations

    Max followed by scientists and thinkers

    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_262k_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
    resume
    0.76
     adoptive
    0.74
     aggressive
    0.73
    =-
    0.73
    aggressive
    0.71
     initiate
    0.71
     continuous
    0.69
     impulsive
    0.67
    stop
    0.67
     cultivation
    0.66
    POSITIVE LOGITS
     menyebut
    0.70
     Hack
    0.68
     ड
    0.66
    lecting
    0.66
     Drei
    0.65
     தென்
    0.65
     steht
    0.64
    setName
    0.64
    ệt
    0.64
    enci
    0.63
    Activations Density 0.000%

    No Known Activations