© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93014
    Prev
    Next
    INDEX
    Explanations

    word sequences

    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
     invitación
    -1.31
     autorización
    -1.21
     devolución
    -1.20
     demselben
    -1.13
     Garantía
    -1.11
     constitución
    -1.08
     estadía
    -1.05
    demic
    -1.05
     recaudación
    -1.05
     inscripción
    -1.04
    POSITIVE LOGITS
    をします
    1.16
    Fifteen
    1.04
     luminos
    1.02
    谏
    1.02
    ができる
    1.02
    ができます
    1.01
    и
    1.01
    showMessage
    0.99
    を行います
    0.99
    cm
    0.97
    Activations Density 0.000%

    No Known Activations