© 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-65K
    7. 2880
    Prev
    Next
    INDEX
    Explanations

    directory name +

    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_65k_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
     exerts
    0.78
     unchallenged
    0.76
    醌
    0.76
    steroidal
    0.75
    솟
    0.75
     feiern
    0.74
    unistd
    0.73
     ausschließlich
    0.72
     freep
    0.72
     दशहरा
    0.71
    POSITIVE LOGITS
     +"
    1.75
     +
    1.67
    +",
    1.55
    +"
    1.52
     +'
    1.31
     +"\
    1.31
    +'
    1.29
    +',
    1.27
     $+$
    1.24
    +"\
    1.22
    Activations Density 0.529%

    No Known Activations