© 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. 25819
    Prev
    Next
    INDEX
    Explanations

    Czech Republic

    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
     so
    -1.26
     with
    -1.22
     (
    -1.21
     in
    -1.15
     without
    -1.03
     supremely
    -1.02
    …？
    -1.02
     undeniably
    -1.01
     people
    -0.97
     make
    -0.94
    POSITIVE LOGITS
     kullanılır
    1.31
     bezahlt
    1.20
    ZIONE
    1.18
    ETTA
    1.15
     erlaubt
    1.15
    堪能
    1.14
     mentre
    1.11
     beantragt
    1.10
     markiert
    1.09
     obligé
    1.09
    Activations Density 0.004%

    No Known Activations