© 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. 20063
    Prev
    Next
    INDEX
    Explanations

    impoverished ex-student; Southeast Styria; concentration; carries; current

    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
    bk
    0.52
    parseInt
    0.50
    hx
    0.46
    know
    0.46
    oughed
    0.46
    vor
    0.45
    1
    0.45
    constant
    0.45
    愈
    0.45
    pard
    0.45
    POSITIVE LOGITS
     OCPP
    0.46
     certi
    0.46
    指揮
    0.45
     eligibility
    0.44
     accreditation
    0.43
     bunting
    0.43
    لان
    0.42
     chock
    0.42
    يديو
    0.42
    olition
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.