© 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. 245178
    Prev
    Next
    INDEX
    Explanations

    VPNs and learning

    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
    segmented
    0.48
    もない
    0.47
    idirectional
    0.45
    ргани
    0.45
    ineau
    0.44
    erus
    0.44
    β
    0.44
    brigen
    0.43
    oursquare
    0.43
    ҙ
    0.43
    POSITIVE LOGITS
     estado
    0.48
    ඇ
    0.47
    මෙ
    0.47
     poč
    0.46
     okazji
    0.45
     kayaks
    0.44
     stanje
    0.43
     Diy
    0.43
     condos
    0.42
    Leer
    0.42
    Activations Density 0.001%

    No Known Activations