© 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. 255305
    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
    _
    0.50
    0.49
    =
    0.48
     recordings
    0.43
    ,..
    0.43
    attitude
    0.43
     =
    0.42
     shew
    0.42
    บ
    0.41
     vulgaris
    0.41
    POSITIVE LOGITS
    মাল
    0.53
    变革
    0.52
     ያስፈል
    0.50
     Mapa
    0.50
     mnogo
    0.47
     funzionamento
    0.47
    সাহিত্য
    0.47
    さまざまな
    0.46
     কথাই
    0.46
    িলারা
    0.46
    Activations Density 0.000%

    No Known Activations