© 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. 188107
    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
     reconnaît
    0.54
    拍卖
    0.53
     пытается
    0.52
    GTBase
    0.52
     ciento
    0.51
    τια
    0.51
    菫
    0.50
     deuxième
    0.50
     фаразлау
    0.49
    κτήθηκε
    0.49
    POSITIVE LOGITS
    ured
    0.54
    sey
    0.44
     crooked
    0.44
     Living
    0.42
    Ком
    0.42
    t
    0.41
    ado
    0.41
     split
    0.41
     insides
    0.41
     inclined
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.