© 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. 4677
    Prev
    Next
    INDEX
    Explanations

    numbers and weeks

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

    numerical units

    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
     lifelong
    0.47
     compet
    0.47
     like
    0.45
     curator
    0.44
     n
    0.43
     patronage
    0.43
     the
    0.42
     reasonable
    0.41
     Abdul
    0.41
     serendip
    0.40
    POSITIVE LOGITS
    秋冬
    0.47
    hình
    0.46
     centerY
    0.46
    িক্স
    0.46
     insectes
    0.45
    瓔
    0.45
    rechts
    0.45
     caoutch
    0.45
    春夏
    0.44
    cgColor
    0.44
    Activations Density 0.000%

    No Known Activations