© 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. 64904
    Prev
    Next
    INDEX
    Explanations

    command line configuration

    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
     gagner
    -1.12
    の基本
    -1.09
     my
    -1.08
     gérer
    -1.06
     Ответить
    -1.05
     geliefert
    -1.05
     appeler
    -1.04
    excellent
    -1.03
     Gå
    -1.03
    即便
    -1.02
    POSITIVE LOGITS
    
    1.20
    fizierung
    1.16
    があり
    1.10
    Durata
    1.10
    jfree
    1.09
     when
    1.08
     onCancelled
    1.05
    による
    1.05
    quần
    1.05
     with
    1.04
    Activations Density 0.014%

    No Known Activations