© 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. 39900
    Prev
    Next
    INDEX
    Explanations

    actions or operations

    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
     faciliter
    -1.60
    albeit
    -1.47
     formules
    -1.44
    THINK
    -1.42
    楽しめる
    -1.39
     recentemente
    -1.39
    这样
    -1.38
     fonde
    -1.38
     GETTING
    -1.37
     😁
    -1.36
    POSITIVE LOGITS
     your
    2.41
     with
    2.03
     all
    1.92
     from
    1.84
     without
    1.84
     as
    1.83
     or
    1.80
     our
    1.70
     one
    1.70
     them
    1.66
    Activations Density 0.037%

    No Known Activations