© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36190
    Prev
    Next
    INDEX
    Explanations

    It is/was followed by observation

    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
     didn
    -1.23
     henvisninger
    -1.22
    taminophen
    -1.17
    <_>
    -1.16
    staben
    -1.13
     to
    -1.10
    skjaer
    -1.09
    เกี่ยวกับ
    -1.09
     vokal
    -1.05
     doesn
    -1.04
    POSITIVE LOGITS
     this
    1.51
    還可以
    1.34
     unable
    1.25
    还可以
    1.21
     lze
    1.19
     can
    1.13
     można
    1.13
     này
    1.13
     ניתן
    1.11
     łatwo
    1.10
    Activations Density 0.056%

    No Known Activations