© 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. 15156
    Prev
    Next
    INDEX
    Explanations

    least squares acronyms

    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
    謖
    -1.82
    ³.
    -1.53
    髣
    -1.51
     destinées
    -1.48
     temporaire
    -1.48
     经典
    -1.46
     简介
    -1.42
     is
    -1.42
     semelhante
    -1.41
     isn
    -1.40
    POSITIVE LOGITS
    </em>
    1.89
     —
    1.58
     niitä
    1.52
     do
    1.45
    ні
    1.37
     we
    1.37
    ,"
    1.34
    肫
    1.34
    our
    1.33
     '
    1.30
    Activations Density 0.133%

    No Known Activations