© 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. 36183
    Prev
    Next
    INDEX
    Explanations

    method, approach, style, technique

    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
     placée
    -1.07
     volgt
    -1.07
     escuro
    -1.04
    ො
    -1.04
    Segue
    -1.04
     embalaje
    -1.03
    τοι
    -1.03
     voldoende
    -1.02
     Послед
    -1.02
    setzungen
    -1.01
    POSITIVE LOGITS
     method
    1.76
     approach
    1.41
     technique
    1.36
     méthode
    1.36
     methods
    1.35
     style
    1.34
     techniques
    1.34
     método
    1.30
     principles
    1.29
    methode
    1.28
    Activations Density 0.086%

    No Known Activations