© 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. 59522
    Prev
    Next
    INDEX
    Explanations

    since then

    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
    )--
    -1.90
    </sup>
    -1.79
    </h2>
    -1.77
    ついで
    -1.60
    こいつ
    -1.55
     (--
    -1.51
     ausreich
    -1.50
     Füßen
    -1.50
    ")]
    -1.49
     takiej
    -1.49
    POSITIVE LOGITS
    k
    1.58
    6
    1.49
    我们
    1.45
     vuol
    1.41
     bunda
    1.40
     méd
    1.35
    被
    1.34
    而
    1.30
    ’
    1.30
     palav
    1.26
    Activations Density 0.010%

    No Known Activations