© 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. 256573
    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
    谭
    0.51
    :%
    0.49
    usher
    0.48
    4
    0.47
    样
    0.47
    krb
    0.47
    gren
    0.46
    7
    0.46
    样品
    0.44
    \%
    0.44
    POSITIVE LOGITS
     penthouse
    0.61
     bereavement
    0.55
     batting
    0.54
     brat
    0.52
     bullpen
    0.52
     superman
    0.51
     ло
    0.50
     batman
    0.50
     retirement
    0.50
     downtown
    0.50
    Activations Density 0.001%

    No Known Activations