© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 73546
    Prev
    Next
    INDEX
    Explanations

    special phrases

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

    base, essential, reality, SAM

    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
     connues
    0.52
     hebdom
    0.49
     BVHTree
    0.47
     Allemagne
    0.47
     ricos
    0.46
     particulières
    0.46
    嚩
    0.45
     Moscou
    0.44
     estatales
    0.44
     入り
    0.44
    POSITIVE LOGITS
    as
    0.61
    a
    0.60
    even
    0.57
    aes
    0.54
    al
    0.53
    ev
    0.52
    ar
    0.51
    basis
    0.50
    element
    0.49
    aa
    0.49
    Activations Density 0.001%

    No Known Activations