© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117444
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and scientific notation

    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
     草莓
    -0.93
     рік
    -0.90
     francus
    -0.87
     Brus
    -0.82
     绘画
    -0.80
     }(\
    -0.79
     τὴν
    -0.79
     Sich
    -0.79
     discípulos
    -0.78
     笔
    -0.77
    POSITIVE LOGITS
     Mr
    1.05
     $_{
    1.01
     τον
    1.00
    msub
    0.93
     ${
    0.84
    ızlık
    0.81
    }_{
    0.78
     $
    0.78
    _${
    0.78
    RICO
    0.77
    Activations Density 0.039%

    No Known Activations