© 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. 44081
    Prev
    Next
    INDEX
    Explanations

    sources, VT, around

    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
     now
    -1.67
     августа
    -1.38
     ngayon
    -1.38
    inerario
    -1.34
    strando
    -1.33
     Ślą
    -1.28
     июля
    -1.28
    VIOUS
    -1.27
    eados
    -1.24
    AppCompatTheme
    -1.23
    POSITIVE LOGITS
    o
    1.56
    e
    1.39
    y
    1.24
     ersten
    1.23
    om
    1.19
     дополнительных
    1.16
     merveilleux
    1.16
    n
    1.15
     housse
    1.14
     любых
    1.14
    Activations Density 0.006%

    No Known Activations