© 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. 146920
    Prev
    Next
    INDEX
    Explanations

    fire department

    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
    ನ್ಸ್
    0.81
    ovirus
    0.75
     Fallon
    0.68
    \"]\
    0.67
    }]{
    0.67
    Margaret
    0.65
     یقین
    0.64
    落
    0.64
    university
    0.64
    ctions
    0.64
    POSITIVE LOGITS
    飨
    0.72
     geschrieben
    0.70
     अम्ब
    0.68
     sou
    0.67
    Aval
    0.67
    ակի
    0.66
    дол
    0.66
     Bevölker
    0.66
    菩
    0.65
     बध
    0.63
    Activations Density 0.001%

    No Known Activations