© 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. 38737
    Prev
    Next
    INDEX
    Explanations

    formats, command, front, my, available, make, 8

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

    production applications and customer

    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
    მოს
    0.48
    bsch
    0.45
    ᠰ
    0.44
    篌
    0.43
    会的
    0.43
     solv
    0.42
    cInfo
    0.42
    zogen
    0.42
    ண்டை
    0.42
    rarse
    0.41
    POSITIVE LOGITS
     Pickup
    0.52
     defunct
    0.46
     và
    0.45
    āya
    0.44
     véritables
    0.44
     véritable
    0.43
    ใช้งาน
    0.43
     এবং
    0.42
     và
    0.42
     и
    0.42
    Activations Density 0.001%

    No Known Activations