© 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. 34-GEMMASCOPE-RES-131K
    7. 11959
    Prev
    Next
    INDEX
    Explanations

    introducing an option, solution, or aspect

    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_34/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
    wasn
    -1.23
     referenties
    -1.23
    remain
    -1.20
    ζα
    -1.17
     THERE
    -1.17
    THERE
    -1.16
    rugu
    -1.14
     jardins
    -1.13
    Ɽ
    -1.13
    weren
    -1.09
    POSITIVE LOGITS
     that
    2.98
     is
    2.30
     worth
    1.84
     frequently
    1.78
     which
    1.70
     often
    1.66
     might
    1.65
     comes
    1.64
     involves
    1.59
     could
    1.59
    Activations Density 0.067%

    No Known Activations