© 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. 208526
    Prev
    Next
    INDEX
    Explanations

    naming calves

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

    describing options or variations

    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
    ）。
    0.48
     천
    0.47
    ानीय
    0.45
     충
    0.44
    두
    0.44
    azione
    0.44
     주요
    0.43
    弧
    0.42
     Zeitpunkt
    0.42
     바
    0.41
    POSITIVE LOGITS
     probate
    0.51
     Plumbing
    0.50
    at
    0.49
    dere
    0.49
    challenged
    0.47
     Airline
    0.47
    proble
    0.46
     plumbers
    0.45
    ro
    0.44
     Airlines
    0.44
    Activations Density 0.001%

    No Known Activations