© 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. 59205
    Prev
    Next
    INDEX
    Explanations

    beginning of sentences

    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
    5
    -1.64
     will
    -1.50
    4
    -1.49
    3
    -1.45
    2
    -1.43
     their
    -1.41
     kanske
    -1.41
     are
    -1.38
     such
    -1.36
    こんばん
    -1.35
    POSITIVE LOGITS
     récemment
    1.70
    </em>
    1.69
    </i>
    1.61
     COMPOUNDS
    1.51
    ведении
    1.51
     and
    1.50
    oció
    1.45
     Frühjahr
    1.45
     тыся
    1.43
    ༀ
    1.43
    Activations Density 0.141%

    No Known Activations