© 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. 22-GEMMASCOPE-RES-131K
    7. 129205
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_22/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
     forsaken
    -1.02
    aucun
    -1.00
    りましたが
    -0.99
     groter
    -0.99
     儿童
    -0.98
    입니다
    -0.97
    ựa
    -0.96
     doesn
    -0.96
    ὸς
    -0.96
    áját
    -0.95
    POSITIVE LOGITS
     бампер
    1.24
    ３
    1.05
     ۱۴۰۰
    1.05
    )
    1.04
     rembour
    1.02
    uç
    0.97
     KeyError
    0.96
     régal
    0.96
    finish
    0.96
    そして
    0.96
    Activations Density 0.004%

    No Known Activations