© 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. 68518
    Prev
    Next
    INDEX
    Explanations

    feature availability or capability

    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
    octet
    -1.05
    meneu
    -0.98
    ţi
    -0.97
     modèles
    -0.95
    Padding
    -0.95
    通常
    -0.94
    …~
    -0.93
    DELIM
    -0.93
    InMillis
    -0.92
    "(
    -0.91
    POSITIVE LOGITS
     availability
    1.55
     capabilities
    1.50
     capability
    1.45
     ability
    1.41
     available
    1.40
     abilities
    1.20
     capable
    1.19
     disponibilità
    1.16
     usable
    1.15
     availa
    1.14
    Activations Density 0.068%

    No Known Activations