© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    roosevelt, roasting, property, proactive

    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
    暂
    0.77
    網路
    0.66
    editable
    0.59
    เส้น
    0.59
    न्ति
    0.57
     Bankers
    0.56
    issau
    0.55
     plaus
    0.55
     Indexed
    0.55
    暫
    0.55
    POSITIVE LOGITS
    okie
    0.91
    PERTY
    0.80
    aches
    0.77
    duc
    0.77
    blems
    0.73
    ducers
    0.72
    perty
    0.71
     وخت
    0.71
    cks
    0.70
     bro
    0.70
    Activations Density 0.101%

    No Known Activations