© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31444
    Prev
    Next
    INDEX
    Explanations

    kilometers and miles

    np_acts-logits-general · gemini-2.5-flash-lite

    distances in miles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fire
    0.37
    進
    0.37
    Fire
    0.36
     clums
    0.36
     aspire
    0.36
     parli
    0.35
     intrigued
    0.35
     negligently
    0.35
     apathy
    0.35
     मेक
    0.34
    POSITIVE LOGITS
    unused
    0.41
    Buildings
    0.40
     কট
    0.40
    databinding
    0.40
    阕
    0.39
    เมือง
    0.39
    ádio
    0.39
     села
    0.38
    phot
    0.38
     río
    0.38
    Activations Density 0.017%

    No Known Activations