© 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. 84129
    Prev
    Next
    INDEX
    Explanations

    summary reports

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

    comparisons and hierarchies

    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
    ar
    0.56
    ла
    0.52
    GA
    0.52
    ra
    0.52
    RA
    0.52
    acion
    0.51
    ée
    0.50
    n
    0.50
    ラ
    0.49
    G
    0.48
    POSITIVE LOGITS
     annualized
    0.52
     congestion
    0.46
     rozwoju
    0.46
     supervising
    0.45
     betterment
    0.45
     зві
    0.44
    routingHeader
    0.44
    stethoscope
    0.43
     Supervisors
    0.43
     характеризу
    0.43
    Activations Density 0.000%

    No Known Activations