© 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. 254827
    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
     willow
    0.44
    вании
    0.43
     небо
    0.43
    ኗ
    0.42
     вода
    0.42
     galima
    0.42
     stable
    0.40
     mole
    0.40
     zealand
    0.40
    杫
    0.40
    POSITIVE LOGITS
    ਨ
    0.59
    ską
    0.53
    ēl
    0.52
     aspirants
    0.52
    कर्मियों
    0.52
    एस
    0.51
    खास्त
    0.49
     വിശദ
    0.49
     UPSC
    0.48
     Tvam
    0.48
    Activations Density 0.000%

    No Known Activations