© 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. 39108
    Prev
    Next
    INDEX
    Explanations

    common starting phrases

    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_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
    և
    -1.23
    ૉ
    -1.20
     rheumat
    -1.18
     will
    -1.15
     citroen
    -1.12
    aikan
    -1.09
     scania
    -1.09
     Græ
    -1.08
    傳統
    -1.07
     cabrio
    -1.04
    POSITIVE LOGITS
     beż
    1.20
    canActivate
    1.16
    ключения
    1.15
    textTheme
    1.14
     getItemCount
    1.12
    nad
    1.12
    oltà
    1.10
     OTHERWISE
    1.09
     soeur
    1.09
    nelse
    1.07
    Activations Density 0.003%

    No Known Activations