© 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. 234831
    Prev
    Next
    INDEX
    Explanations

    purpose or location

    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
     干
    0.44
     သူ
    0.43
     こちら
    0.43
    ских
    0.42
     Chr
    0.42
    KT
    0.41
     C
    0.41
     RH
    0.41
     kT
    0.41
     chr
    0.41
    POSITIVE LOGITS
    ında
    0.55
    gação
    0.52
    देश
    0.48
    dades
    0.47
    Interfaz
    0.45
    ജ്
    0.45
     amores
    0.44
     amaç
    0.44
    ದಗ
    0.44
     ок
    0.43
    Activations Density 0.000%

    No Known Activations