© 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. 59053
    Prev
    Next
    INDEX
    Explanations

    applications and programs

    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
     method
    -1.73
     prata
    -1.52
    ="
    -1.49
    ."
    -1.48
     so
    -1.45
    水墨
    -1.39
     modele
    -1.39
     proje
    -1.38
     fase
    -1.38
    )=\
    -1.38
    POSITIVE LOGITS
     esenciales
    1.64
    audiovisuel
    1.55
     necesarios
    1.52
    擄
    1.47
     (
    1.45
     necesarias
    1.41
     bestimm
    1.40
    ള്
    1.39
     angegebenen
    1.38
     perfeitamente
    1.38
    Activations Density 0.101%

    No Known Activations