© 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. 16229
    Prev
    Next
    INDEX
    Explanations

    specific token followed by another

    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
     our
    -1.68
     atlet
    -1.55
     usai
    -1.53
     even
    -1.45
     spirituelle
    -1.35
    硕士
    -1.35
     soyez
    -1.31
    佥
    -1.29
     we
    -1.26
     diskon
    -1.25
    POSITIVE LOGITS
    ּוֹ
    1.58
    ִּ
    1.57
    ֶּ
    1.40
    ַּ
    1.38
    AAD
    1.27
    וּ
    1.27
    berd
    1.22
     turístico
    1.21
    küche
    1.21
     бампер
    1.20
    Activations Density 0.000%

    No Known Activations