© 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. 145740
    Prev
    Next
    INDEX
    Explanations

    accept answers

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

    indicates characteristic or definition

    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
    x
    0.47
    各自
    0.46
    v
    0.46
    ts
    0.45
    ij
    0.45
    io
    0.43
    iration
    0.43
    mp
    0.43
    ib
    0.42
    áz
    0.42
    POSITIVE LOGITS
     consiste
    0.64
     состоит
    0.52
     består
    0.50
    時は
    0.47
     dédiée
    0.47
    كلمنا
    0.47
     znači
    0.46
     definido
    0.46
    轵
    0.46
     definito
    0.45
    Activations Density 0.001%

    No Known Activations