© 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. 65861
    Prev
    Next
    INDEX
    Explanations

    technical terms and foreign words

    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
     апреля
    -1.28
    iſter
    -1.26
    ^'
    -1.20
     onSubmit
    -1.19
    鯰
    -1.18
    𝙒
    -1.17
    òa
    -1.17
    niques
    -1.16
    pham
    -1.16
     with
    -1.15
    POSITIVE LOGITS
    <bos>
    1.21
    ist
    1.17
    ur
    1.17
    uo
    1.13
     coisas
    1.05
    添加
    1.02
     hôn
    1.02
     government
    1.02
    ge
    1.01
    駄
    1.01
    Activations Density 0.001%

    No Known Activations