© 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. 146198
    Prev
    Next
    INDEX
    Explanations

    Bonobo and blue `#3498db`

    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
    ceau
    0.74
    ɩ
    0.72
    memor
    0.72
     входит
    0.72
    KES
    0.72
    kem
    0.71
    Hearing
    0.71
    <unused58>
    0.70
    メートル
    0.70
    wend
    0.70
    POSITIVE LOGITS
    RP
    0.61
     налич
    0.58
     vivir
    0.58
    ductor
    0.57
     Physiology
    0.56
     Physic
    0.55
     생
    0.54
    ዖ
    0.54
     Physical
    0.54
    rück
    0.54
    Activations Density 0.003%

    No Known Activations