© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3642
    Prev
    Next
    INDEX
    Explanations

    Project Text

    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
    郋
    0.74
    nnc
    0.71
     lieux
    0.69
    Rich
    0.69
     RPG
    0.69
    நர்
    0.67
     Manfred
    0.67
     Arrival
    0.66
     OSHA
    0.65
     Neighbor
    0.64
    POSITIVE LOGITS
     peace
    0.93
     PEACE
    0.90
    💓
    0.83
    ❤️❤️
    0.80
    😘
    0.80
    peace
    0.76
     Peace
    0.75
     😘
    0.74
    💗
    0.74
    tym
    0.73
    Activations Density 0.085%

    No Known Activations