© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72363
    Prev
    Next
    INDEX
    Explanations

    H, male, project, Sul, Arabs

    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
     向け
    -1.91
    –
    -1.84
     に関する
    -1.66
     dirit
    -1.49
    Also
    -1.45
     ombro
    -1.42
     exacte
    -1.41
     ondu
    -1.41
    -
    -1.38
    Other
    -1.37
    POSITIVE LOGITS
     kleding
    1.72
     voedsel
    1.65
     bloemen
    1.63
     pakaian
    1.52
     fermée
    1.35
     merasa
    1.33
     値下げ
    1.33
     fermés
    1.31
     keuken
    1.31
    )
    1.30
    Activations Density 36.804%

    No Known Activations