© 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. 21329
    Prev
    Next
    INDEX
    Explanations

    Jai brand

    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
     that
    -1.49
    _
    -1.38
     intenso
    -1.38
    ánchez
    -1.27
    促销
    -1.25
     extensively
    -1.24
     één
    -1.23
     \
    -1.23
    r
    -1.23
    𝒽
    -1.19
    POSITIVE LOGITS
     the
    2.02
     незавер
    1.59
    ]:
    1.52
     abitanti
    1.43
     Einige
    1.41
    まずは
    1.40
    })$
    1.35
     actuels
    1.35
    UCIÓN
    1.34
    \}$,
    1.34
    Activations Density 0.016%

    No Known Activations