© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3893
    Prev
    Next
    INDEX
    Explanations

    various topics, often with specific actors or roles

    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
     ever
    0.71
     God
    0.63
    4
    0.61
     cut
    0.59
    Sir
    0.58
     sir
    0.58
    ጹ
    0.58
    atorias
    0.57
     y
    0.57
     Dec
    0.57
    POSITIVE LOGITS
    stered
    0.88
     PSC
    0.82
     medallion
    0.79
    istered
    0.79
     poked
    0.79
    uslar
    0.79
     pietra
    0.78
     Mình
    0.78
     bling
    0.77
    燻
    0.77
    Activations Density 0.001%

    No Known Activations