© 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. 163554
    Prev
    Next
    INDEX
    Explanations

    real estate, earn through, spiritual learning, PMIEF Learning

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

    analysis issues

    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
    nt
    0.71
    sh
    0.63
    t
    0.63
    ng
    0.56
    ss
    0.53
    ui
    0.53
    src
    0.53
    de
    0.53
    ri
    0.52
    sum
    0.52
    POSITIVE LOGITS
    ScriptBuf
    0.54
     نما
    0.53
     Buddhists
    0.51
     astrophys
    0.50
     музыкан
    0.50
     pendants
    0.50
     대부분
    0.49
    🦾
    0.49
     اکث
    0.49
     eigenvectors
    0.49
    Activations Density 0.000%

    No Known Activations