© 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. 129713
    Prev
    Next
    INDEX
    Explanations

    network side

    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
     Only
    -2.00
    </b>
    -1.81
     occhiali
    -1.79
     However
    -1.75
     Then
    -1.65
    !
    -1.63
     TWO
    -1.62
     Græ
    -1.59
     sterben
    -1.57
    人們
    -1.57
    POSITIVE LOGITS
    ឵
    2.22
    昻
    1.98
    titial
    1.95
    いえば
    1.93
    as
    1.91
    ſſen
    1.91
    but
    1.90
    despite
    1.86
    ちょこ
    1.86
    often
    1.84
    Activations Density 0.009%

    No Known Activations