© 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. 15173
    Prev
    Next
    INDEX
    Explanations

    springframework

    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
     to
    -1.63
     from
    -1.46
    tový
    -1.34
     aldri
    -1.30
    harusnya
    -1.27
     the
    -1.26
    itattu
    -1.26
     уже
    -1.23
    meisterschaften
    -1.23
    prnewswire
    -1.22
    POSITIVE LOGITS
     it
    1.59
     
    1.48
    摸了
    1.41
    を行い
    1.32
    があります
    1.32
    \
    1.30
    tolo
    1.27
    が見える
    1.27
    があり
    1.26
    がありますが
    1.25
    Activations Density 0.003%

    No Known Activations