© 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. 174322
    Prev
    Next
    INDEX
    Explanations

    safety, daily, without

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

    paperback, relay, generously, commitment, last

    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
    anye
    0.61
    JobList
    0.55
    પણ
    0.49
    は
    0.45
    ppled
    0.44
    चारी
    0.44
    Suggestions
    0.44
    Cancel
    0.43
    '
    0.42
    Job
    0.42
    POSITIVE LOGITS
     Aws
    0.50
     Mediterranean
    0.50
    ijske
    0.49
     不同
    0.47
     Daylight
    0.46
     Suns
    0.46
    ිනි
    0.46
     Mediterr
    0.45
     Elastic
    0.45
    ز
    0.45
    Activations Density 0.000%

    No Known Activations