© 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. 33500
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    including
    -1.25
    patrón
    -1.22
    Longueur
    -1.21
    Largeur
    -1.20
     bénéfic
    -1.20
    corazón
    -1.15
     Fácil
    -1.14
     Matériau
    -1.11
    Fácil
    -1.10
    comfortably
    -1.10
    POSITIVE LOGITS
     who
    1.08
     there
    0.90
    coins
    0.90
     services
    0.89
    -------
    0.86
    ?.
    0.85
    set
    0.85
    se
    0.85
     document
    0.85
     certainly
    0.84
    Activations Density 0.097%

    No Known Activations