© 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. 137902
    Prev
    Next
    INDEX
    Explanations

    enrollment or eligibility information

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

    training enrollment

    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
    ८
    0.50
    ."'
    0.48
    izm
    0.45
    מ
    0.44
    .'
    0.44
    
    0.44
    гідно
    0.42
    /'
    0.42
    מס
    0.42
    Зна
    0.41
    POSITIVE LOGITS
     enroll
    0.49
     enrolling
    0.47
     enrolment
    0.46
     improving
    0.46
     soli
    0.44
     emberek
    0.44
     sam
    0.42
     eligibility
    0.42
     zlep
    0.41
     Mocha
    0.41
    Activations Density 0.000%

    No Known Activations