© 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. 256558
    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
    জাত
    0.55
    炵
    0.54
    如今
    0.49
    猶
    0.48
    卵
    0.47
    以色列
    0.47
    投資
    0.46
    Israel
    0.46
    FLP
    0.46
    専門店
    0.46
    POSITIVE LOGITS
     ENC
    0.53
     ۱
    0.51
     Rails
    0.46
     REF
    0.46
     PUN
    0.45
    лер
    0.45
     erased
    0.45
    ritional
    0.44
    ónio
    0.43
     PUR
    0.42
    Activations Density 0.000%

    No Known Activations