© 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. 260785
    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
    ക്കേണ്ട
    0.42
    successor
    0.41
    ൊന്നും
    0.40
     dunque
    0.38
    ়া
    0.38
    춧
    0.38
    了好
    0.38
     ماذا
    0.38
     क्रिप्टो
    0.37
    したので
    0.37
    POSITIVE LOGITS
    ét
    0.44
     ปลา
    0.42
    ök
    0.41
     are
    0.40
    activité
    0.40
    Ồ
    0.40
     obserw
    0.38
    .
    0.38
    ódigo
    0.38
     drawSprites
    0.38
    Activations Density 0.000%

    No Known Activations