© 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. 164095
    Prev
    Next
    INDEX
    Explanations

    tracking vehicles

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

    drying item

    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
    es
    0.52
    replic
    0.51
     replica
    0.50
    qw
    0.50
    replica
    0.50
    eniu
    0.49
     ribu
    0.49
     z
    0.49
     mira
    0.49
    ר
    0.49
    POSITIVE LOGITS
     ఎన్నిక
    0.49
    бліоте
    0.47
     Lessor
    0.45
     हल्ला
    0.45
     దో
    0.44
    ikko
    0.43
     Welfare
    0.43
     Coates
    0.43
    ights
    0.42
     परेड
    0.42
    Activations Density 0.000%

    No Known Activations