© 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. 259819
    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
    n
    0.46
                 
    0.44
    $`
    0.43
     &.
    0.41
    ¼
    0.40
     inhomogeneity
    0.40
     matter
    0.40
     Oregon
    0.40
    &)
    0.40
    NB
    0.39
    POSITIVE LOGITS
     আওয়
    0.55
     Tattha
    0.53
     Президента
    0.51
     বিক্রয়
    0.50
     ಎಂದ
    0.50
     Einwill
    0.50
     उसमे
    0.49
    raising
    0.49
    ţi
    0.48
     పాల్
    0.48
    Activations Density 0.000%

    No Known Activations