© 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. 14001
    Prev
    Next
    INDEX
    Explanations

    predictable, standard, generic

    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
    了两
    -1.03
    phòng
    -0.91
     permitan
    -0.90
    ETERS
    -0.89
    quam
    -0.86
    ωμα
    -0.85
     requerimientos
    -0.85
    timmen
    -0.85
     october
    -0.85
    roen
    -0.85
    POSITIVE LOGITS
     standard
    1.41
     стандарт
    1.30
     predictable
    1.24
    standard
    1.22
     deja
    1.06
     similar
    1.04
     generic
    1.04
    Standard
    1.03
     typical
    1.02
     typique
    1.02
    Activations Density 0.042%

    No Known Activations