© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65962
    Prev
    Next
    INDEX
    Explanations

    ex vivo

    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
     a
    -2.11
    requipa
    -1.77
     "
    -1.73
    gencias
    -1.63
     -
    -1.55
    izaron
    -1.42
     cantora
    -1.41
     on
    -1.39
     “
    -1.38
     Verhältnis
    -1.35
    POSITIVE LOGITS
    if
    1.69
     esigen
    1.56
    回目の
    1.41
     Poznań
    1.40
    就會
    1.38
     distinguir
    1.38
     tylko
    1.34
     there
    1.34
     حتی
    1.33
    probieren
    1.33
    Activations Density 0.152%

    No Known Activations