© 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. 70470
    Prev
    Next
    INDEX
    Explanations

    figure/panel labels followed by illustration

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

    programming, technical terms, and concepts

    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
    POSIX
    0.45
    混
    0.43
     adjudication
    0.42
    NAT
    0.41
     physical
    0.39
     bif
    0.39
    ेंडर
    0.39
     cardiac
    0.39
     מת
    0.39
     federal
    0.38
    POSITIVE LOGITS
     (
    0.47
     neuer
    0.44
     préparations
    0.44
     esimerkiksi
    0.42
     («
    0.41
     esimerk
    0.41
     propriétaire
    0.41
     lancio
    0.41
     préstamo
    0.41
    実感
    0.40
    Activations Density 0.001%

    No Known Activations