© 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. 34-GEMMASCOPE-RES-131K
    7. 47496
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
     fifth
    -1.15
     Fifth
    -1.14
    Fifth
    -1.12
    fifth
    -0.94
     five
    -0.85
    ñores
    -0.83
    ⑤
    -0.81
     пя
    -0.80
     FIFTH
    -0.78
     beş
    -0.78
    POSITIVE LOGITS
    7
    1.74
    6
    1.44
    七十
    1.16
     seventy
    1.13
     seven
    1.11
     seventies
    1.05
     soixante
    1.02
     Seventy
    0.94
    <0x8D>
    0.92
     Seven
    0.88
    Activations Density 0.057%

    No Known Activations