© 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. 112079
    Prev
    Next
    INDEX
    Explanations

    community and personal attributes

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

    concentration, outcome, lands

    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
     Zeitpunkt
    0.50
     entfernt
    0.50
     korrekt
    0.49
     klasse
    0.48
     Hinter
    0.46
    팬
    0.46
    ని
    0.45
     Viktor
    0.44
     Polskiej
    0.44
     nooit
    0.44
    POSITIVE LOGITS
    铊
    0.50
    MEs
    0.50
    ipu
    0.49
     ಥ
    0.48
    Mb
    0.47
    GAR
    0.47
     透
    0.46
    ocolate
    0.46
     बालो
    0.46
    antad
    0.46
    Activations Density 0.000%

    No Known Activations