© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129969
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extranjera
    -1.15
     keç
    -1.13
    AxisSize
    -1.13
     roba
    -1.09
    знание
    -1.08
     plafon
    -1.06
     vulgaires
    -1.05
     senin
    -1.05
     rembour
    -1.04
     saisi
    -1.02
    POSITIVE LOGITS
    :
    1.09
    9
    1.05
    2
    1.05
     erlä
    1.05
     prodigy
    0.99
    ׳
    0.95
    7
    0.94
     bearers
    0.94
    var
    0.93
    …
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.