© 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. 152382
    Prev
    Next
    INDEX
    Explanations

    after, on, by, other

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

    account aggregation

    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
    Cómo
    0.55
    rams
    0.53
    m
    0.52
    л
    0.52
    cómo
    0.51
    l
    0.51
    el
    0.50
    lr
    0.50
     کس
    0.50
     Крем
    0.50
    POSITIVE LOGITS
     clinician
    0.53
     pursuant
    0.51
     versie
    0.50
     pazienti
    0.49
     consentement
    0.48
     thèse
    0.48
     licensure
    0.48
     postdoctoral
    0.47
    နစ်
    0.47
     organisme
    0.47
    Activations Density 0.001%

    No Known Activations