© 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. 260407
    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
    and
    0.46
    ,
    0.45
     spokesman
    0.44
    it
    0.43
    an
    0.42
    from
    0.41
    ↵
    0.41
     and
    0.41
    r
    0.41
     и
    0.40
    POSITIVE LOGITS
     nossas
    0.62
     nuestras
    0.58
     nossos
    0.56
     nostre
    0.56
     ہماری
    0.55
     naše
    0.55
     våra
    0.53
     vores
    0.52
     ہمارے
    0.51
     naszej
    0.51
    Activations Density 0.000%

    No Known Activations