© 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. 22076
    Prev
    Next
    INDEX
    Explanations

    what all

    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
     Because
    -1.63
     one
    -1.61
     if
    -1.60
     otra
    -1.55
     otro
    -1.48
     high
    -1.36
     From
    -1.34
     While
    -1.27
     một
    -1.24
    歌手
    -1.24
    POSITIVE LOGITS
    </h2>
    1.61
     :}
    1.54
    哪些
    1.47
    </b>
    1.44
     inkluder
    1.38
     naše
    1.37
     哪些
    1.34
    짐
    1.34
    cluding
    1.32
    tefan
    1.32
    Activations Density 0.026%

    No Known Activations