© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44759
    Prev
    Next
    INDEX
    Explanations

    hex2dec, tojson, string2Bin

    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
    joyed
    -1.50
    !),
    -1.45
    »,
    -1.45
    鐽
    -1.41
    (");
    -1.41
     and
    -1.41
    认知
    -1.40
     ā
    -1.39
    '),
    -1.38
     (?)
    -1.38
    POSITIVE LOGITS
     Fazit
    1.74
     Lernen
    1.64
     our
    1.64
     appelez
    1.63
    Other
    1.62
    𐄙
    1.58
     Nachhal
    1.58
     Versuche
    1.53
     Concerning
    1.51
     häufigsten
    1.50
    Activations Density 0.022%

    No Known Activations