© 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. 252825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Baths
    0.52
     couches
    0.51
     EMBO
    0.48
     respirator
    0.47
    '
    0.47
     bathroom
    0.46
    wiches
    0.46
     Escol
    0.46
     powered
    0.44
     Bath
    0.44
    POSITIVE LOGITS
    hav
    0.52
    મ
    0.50
    数値
    0.48
    י
    0.47
    ている
    0.46
    फ
    0.46
    ション
    0.45
    ウエスト
    0.45
    揣
    0.45
    tmpobj
    0.44
    Activations Density 0.000%

    No Known Activations