© 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. 10-GEMMASCOPE-RES-131K
    7. 101144
    Prev
    Next
    INDEX
    Explanations

    academics, innovators, or commentators

    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
     speziellen
    -2.59
     geringen
    -2.45
    ).
    -2.38
    ↵↵
    -2.25
    that
    -2.23
     traditionellen
    -2.22
     größeren
    -2.20
     longterm
    -2.17
     hochwer
    -2.17
    это
    -2.16
    POSITIVE LOGITS
    0
    2.22
    我一直
    2.20
     kroner
    2.20
    跸
    2.16
     utilizzati
    2.14
     tidak
    2.08
    ?”
    2.08
     russe
    2.06
     tabel
    2.03
    us
    2.02
    Activations Density 0.004%

    No Known Activations