© 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. 10-GEMMASCOPE-RES-131K
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    being away or far

    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_10/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
     glauben
    -1.35
    zeniami
    -1.33
    珦
    -1.31
     före
    -1.29
     voulais
    -1.23
     rodillas
    -1.22
     dizer
    -1.20
    咴
    -1.20
     适合
    -1.19
     szint
    -1.15
    POSITIVE LOGITS
     where
    1.49
     émission
    1.28
    cture
    1.14
     how
    1.13
     was
    1.13
     for
    1.12
     kemampuan
    1.11
     urusan
    1.10
    جاه
    1.09
    ging
    1.09
    Activations Density 0.045%

    No Known Activations