© 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. 10-GEMMASCOPE-RES-131K
    7. 7933
    Prev
    Next
    INDEX
    Explanations

    questions and instructions

    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
     않았
    -1.49
     trompe
    -1.41
     paulo
    -1.40
     temb
    -1.35
     graden
    -1.34
    $,
    -1.33
     fuit
    -1.32
     faç
    -1.32
     inverte
    -1.31
     documental
    -1.31
    POSITIVE LOGITS
     its
    1.91
     it
    1.55
     was
    1.42
     hogares
    1.41
    Its
    1.41
     acoged
    1.35
     reseña
    1.34
     merece
    1.33
     breiten
    1.32
     indicado
    1.31
    Activations Density 0.098%

    No Known Activations