© 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. 44481
    Prev
    Next
    INDEX
    Explanations

    only a single

    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
    prender
    -1.30
     fei
    -1.29
    Arts
    -1.24
     igr
    -1.24
     was
    -1.21
     zyn
    -1.20
    melde
    -1.20
    scriptcase
    -1.19
     Spani
    -1.18
     vort
    -1.18
    POSITIVE LOGITS
     but
    1.63
    緞
    1.38
    兩種
    1.34
     on
    1.30
     a
    1.29
    橢
    1.26
     Only
    1.26
    となります
    1.23
     çocuklar
    1.23
    organizzazione
    1.22
    Activations Density 0.050%

    No Known Activations