© 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-262K
    7. 146766
    Prev
    Next
    INDEX
    Explanations

    engine and engineered

    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_262k_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
    ní
    1.01
    mActivity
    1.01
    сибо
    1.00
     evidence
    0.98
    Evidence
    0.97
    கிறது
    0.96
    evidence
    0.96
    🏻
    0.95
     Evidence
    0.93
     кел
    0.90
    POSITIVE LOGITS
     room
    1.43
     compartment
    1.27
     crankshaft
    1.22
     rooms
    1.18
    ered
    1.15
     cowling
    1.06
    configFile
    1.05
     Room
    1.05
    bells
    1.02
    room
    1.01
    Activations Density 0.010%

    No Known Activations