© 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. 190079
    Prev
    Next
    INDEX
    Explanations

    budget report

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

    business meeting discussions

    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
     doctrines
    0.47
    राजनी
    0.46
    irittura
    0.44
     პარ
    0.43
    ሎ
    0.43
     древ
    0.42
    '$,
    0.41
    ieurs
    0.41
     "&#
    0.41
    úly
    0.41
    POSITIVE LOGITS
     herewith
    0.48
     للت
    0.47
     thanked
    0.47
     received
    0.46
     report
    0.46
    report
    0.45
     Bericht
    0.44
     अवगत
    0.44
     ater
    0.44
     রিপোর্ট
    0.43
    Activations Density 0.076%

    No Known Activations