© 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. 13460
    Prev
    Next
    INDEX
    Explanations

    Counter, Eva, Applying, metacognition

    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
     both
    -1.47
     just
    -1.47
     from
    -1.35
     steadily
    -1.33
     before
    -1.33
     usually
    -1.33
     mostly
    -1.27
     by
    -1.27
     get
    -1.24
     typically
    -1.22
    POSITIVE LOGITS
     élar
    1.32
     meninos
    1.26
     comienzan
    1.23
     piensan
    1.20
     assurent
    1.16
     véhic
    1.16
     revamped
    1.14
     sufren
    1.13
    ''''
    1.11
     zincir
    1.10
    Activations Density 0.000%

    No Known Activations