© 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. 79636
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     by
    -1.30
     because
    -1.27
     when
    -1.17
     during
    -1.16
     showed
    -1.13
     can
    -1.13
     with
    -1.13
     pubblic
    -1.04
     or
    -1.04
     through
    -1.02
    POSITIVE LOGITS
     sooo
    1.13
     deliciously
    1.09
     soooo
    1.07
     изготов
    1.01
     horrid
    1.01
     VERY
    1.01
     プリント
    1.01
     recens
    1.00
     steeds
    1.00
     insanely
    0.98
    Activations Density 0.001%

    No Known Activations