© 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. 256200
    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
    臂
    0.46
    日時
    0.46
    网友
    0.46
     Snack
    0.42
     Antioxid
    0.42
    धीरे
    0.42
    粞
    0.41
    datas
    0.41
    jResponse
    0.41
    弊
    0.40
    POSITIVE LOGITS
     utilisent
    0.55
     après
    0.53
     შეს
    0.52
     électronique
    0.51
     köş
    0.51
     incluida
    0.50
    agré
    0.50
     sonor
    0.50
     aner
    0.49
    IL
    0.48
    Activations Density 0.000%

    No Known Activations