© 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. 98468
    Prev
    Next
    INDEX
    Explanations

    former, Canadian, Chinese, Catholic, based

    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
     such
    -1.69
     others
    -1.36
    such
    -1.25
     столь
    -1.24
     TÉCNICA
    -1.23
    ≦
    -1.23
    these
    -1.22
     LIABLE
    -1.22
    ggy
    -1.16
    ㈲
    -1.16
    POSITIVE LOGITS
    さんから
    1.12
     ErrInvalid
    1.12
     longstanding
    1.11
    føring
    1.08
    はこちらから
    1.07
     Democratic
    1.05
     Following
    1.03
    ее
    1.02
    亿
    1.00
    ом
    0.98
    Activations Density 0.183%

    No Known Activations