© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    seek help and connect

    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
    流域
    0.75
    quiry
    0.73
    此次
    0.72
    ಶ್ಯ
    0.72
    ើម
    0.72
     inquiry
    0.71
    /*
    0.71
     investigating
    0.71
    睜
    0.71
     investigation
    0.71
    POSITIVE LOGITS
     Seek
    0.95
     seek
    0.95
    Seek
    0.91
    寻求
    0.88
     connect
    0.87
    connect
    0.87
     receive
    0.85
    Connect
    0.85
    Receive
    0.84
     Connect
    0.81
    Activations Density 0.043%

    No Known Activations