© 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. 255170
    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
     zoo
    0.48
     മ
    0.46
    တီ
    0.45
     ഇന്ത്യ
    0.44
     scene
    0.44
    bin
    0.42
     pol
    0.42
     బ్రి
    0.41
     장면
    0.41
     residency
    0.41
    POSITIVE LOGITS
    ного
    0.61
    ૫
    0.55
    ２
    0.55
    ５
    0.55
    λή
    0.51
    Agregar
    0.51
    ４
    0.50
    нала
    0.50
    ragen
    0.50
     agrad
    0.50
    Activations Density 0.000%

    No Known Activations