© 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. 100179
    Prev
    Next
    INDEX
    Explanations

    from... to.

    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
     erwähnten
    -1.29
    (…)
    -1.27
    Technologies
    -1.26
    ⻑
    -1.26
     quello
    -1.26
     genitori
    -1.25
    يري
    -1.23
     beiden
    -1.23
    mittag
    -1.23
     мной
    -1.23
    POSITIVE LOGITS
     we
    1.84
     are
    1.51
     was
    1.38
    </h4>
    1.37
     \&
    1.35
    Our
    1.30
     هذه
    1.26
    зация
    1.22
    we
    1.22
     &&
    1.21
    Activations Density 0.051%

    No Known Activations