© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79900
    Prev
    Next
    INDEX
    Explanations

    rank or stage descriptor

    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
    aneity
    -1.23
    swire
    -1.15
    Willkommen
    -1.12
     various
    -1.11
     şun
    -1.10
     üblichen
    -1.09
    就可以了
    -1.09
     LIABLE
    -1.08
    Servus
    -1.08
    Guarda
    -1.06
    POSITIVE LOGITS
     which
    2.31
     whose
    1.56
    ซึ่ง
    1.54
     who
    1.47
     for
    1.45
     and
    1.38
     котором
    1.36
     from
    1.25
     которых
    1.25
     whom
    1.16
    Activations Density 0.086%

    No Known Activations