© 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. 72156
    Prev
    Next
    INDEX
    Explanations

    section headings and technical terms

    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
     interactiva
    -1.05
    datable
    -1.04
    ของ
    -1.00
     process
    -0.98
    leine
    -0.96
    unjung
    -0.96
     effekt
    -0.96
     corporativa
    -0.96
     Tenggara
    -0.96
     thut
    -0.96
    POSITIVE LOGITS
    を見ながら
    1.18
    envie
    1.12
     now
    1.12
     we
    1.11
    encre
    1.09
    になりますが
    1.09
    ))){
    1.08
    艄
    1.08
    examined
    1.05
     vytvoř
    1.05
    Activations Density 0.000%

    No Known Activations