© 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. 70356
    Prev
    Next
    INDEX
    Explanations

    it and/or

    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
     kunna
    -1.32
     pouvoir
    -1.21
     kunne
    -1.14
    都在
    -1.12
    能够
    -1.09
     всем
    -1.03
     automatisch
    -1.00
    檚
    -0.99
     hefyd
    -0.98
     abuelo
    -0.98
    POSITIVE LOGITS
     if
    2.23
     easily
    2.13
     without
    2.03
     by
    1.90
     be
    1.59
     but
    1.45
     with
    1.45
     dowol
    1.37
     through
    1.30
    without
    1.30
    Activations Density 0.431%

    No Known Activations