© 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. 35596
    Prev
    Next
    INDEX
    Explanations

    how [explanation]

    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
    因为它
    -1.50
     when
    -1.38
     ***!
    -1.32
    ;*
    -1.21
    >';
    -1.19
    ❣
    -1.19
     veckan
    -1.17
    (''),
    -1.17
    inerario
    -1.16
     ||
    -1.16
    POSITIVE LOGITS
     each
    1.62
    each
    1.51
     our
    1.50
     these
    1.33
     certaines
    1.26
    があり
    1.23
     acoso
    1.23
     certain
    1.22
    Certain
    1.21
     inapropiados
    1.19
    Activations Density 0.050%

    No Known Activations