© 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. 2348
    Prev
    Next
    INDEX
    Explanations

    designed source

    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
     considérable
    0.68
    σωπ
    0.68
    にて
    0.67
     disparate
    0.65
    Apply
    0.65
     sharedInstance
    0.65
     방법에
    0.65
    蒞
    0.64
    檻
    0.63
    বাসী
    0.63
    POSITIVE LOGITS
     designed
    2.83
    designed
    2.61
     Designed
    2.58
    Designed
    2.50
     conçu
    2.13
     diseñado
    2.08
     conç
    2.00
     diseñada
    1.99
     engineered
    1.75
     aimed
    1.70
    Activations Density 1.280%

    No Known Activations