© 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. 10-GEMMASCOPE-RES-131K
    7. 20144
    Prev
    Next
    INDEX
    Explanations

    version numbers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     You
    -2.25
     touted
    -2.16
     biggest
    -2.06
     Then
    -2.05
     This
    -1.92
     However
    -1.92
    le
    -1.87
     would
    -1.83
     )
    -1.82
     seemed
    -1.82
    POSITIVE LOGITS
    ’
    2.22
     diki
    2.11
    饜
    2.02
     yyq
    2.00
     parachoque
    1.99
     paragraphe
    1.96
     abiye
    1.96
     kere
    1.95
     SDLK
    1.95
    heiser
    1.93
    Activations Density 0.040%

    No Known Activations