© 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. 259932
    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
     realizes
    0.49
     Sì
    0.44
     condemns
    0.43
     }{}_{\
    0.43
    enan
    0.43
    いは
    0.42
     İm
    0.41
    iqi
    0.40
    。
    0.40
     കു
    0.40
    POSITIVE LOGITS
    Australian
    0.59
    Aloe
    0.57
    Transparent
    0.53
    "<
    0.52
    Austral
    0.51
    مارات
    0.50
    лот
    0.50
    ബാ
    0.50
    Latch
    0.50
    Vad
    0.50
    Activations Density 0.000%

    No Known Activations