© 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. 34-GEMMASCOPE-RES-131K
    7. 49721
    Prev
    Next
    INDEX
    Explanations

    units digit calculation

    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_34/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
    睥
    -0.85
     its
    -0.82
     chặt
    -0.82
     nacionais
    -0.79
     colectivo
    -0.77
    tt
    -0.76
    買う
    -0.75
     welches
    -0.75
    the
    -0.75
     archived
    -0.75
    POSITIVE LOGITS
    gerichte
    0.88
    ECG
    0.87
    CZE
    0.86
    ärer
    0.85
    ROI
    0.84
     Ā
    0.84
    DFA
    0.84
    positionen
    0.83
     gestión
    0.83
    gebene
    0.82
    Activations Density 0.171%

    No Known Activations