© 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. 164794
    Prev
    Next
    INDEX
    Explanations

    screenings, work, participation, memory

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

    essential for

    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
     Dalit
    0.52
    泂
    0.50
    ශ්‍ය
    0.49
     गलत
    0.45
    𝚈
    0.45
    צור
    0.44
    常见
    0.44
     tirelessly
    0.44
    共通
    0.44
     searchObject
    0.43
    POSITIVE LOGITS
     buyer
    0.47
     buyers
    0.46
     bead
    0.46
     pavement
    0.42
     purchasers
    0.42
    g
    0.42
     beads
    0.41
     regulators
    0.41
     पहनने
    0.41
     marque
    0.40
    Activations Density 0.001%

    No Known Activations