© 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. 248814
    Prev
    Next
    INDEX
    Explanations

    the Nazarene whom

    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
    yel
    0.52
    뢰
    0.46
    flight
    0.46
    beek
    0.45
    ಸ್ತು
    0.45
    et
    0.45
    Elis
    0.45
    Advertising
    0.44
    落ち着
    0.44
    霍
    0.43
    POSITIVE LOGITS
     ช
    0.57
     Canine
    0.55
     संबंधी
    0.53
     screenings
    0.51
     Plasma
    0.50
     Highways
    0.50
     Picture
    0.50
     Packs
    0.50
     всем
    0.49
     Channels
    0.49
    Activations Density 0.000%

    No Known Activations