© 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. 25718
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation structure

    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
     subió
    -1.05
     несколь
    -1.04
    structura
    -1.02
     الجيش
    -1.02
    Obsah
    -1.01
    OTTEN
    -1.01
     vermutlich
    -1.00
    zzzz
    -0.99
    zzjoni
    -0.99
    opie
    -0.99
    POSITIVE LOGITS
    ここで
    1.13
    就行了
    1.10
     alltså
    1.07
    Él
    1.04
    ні
    1.02
     seyn
    1.02
     waschen
    0.99
    iibo
    0.98
     další
    0.96
    Menurutnya
    0.96
    Activations Density 0.101%

    No Known Activations