© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99239
    Prev
    Next
    INDEX
    Explanations

    contrasting descriptions

    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
     pernic
    -1.73
    が
    -1.70
    ternut
    -1.68
    lihood
    -1.63
    melons
    -1.55
     pérd
    -1.52
    を
    -1.52
    mability
    -1.51
    itisation
    -1.50
    なので
    -1.48
    POSITIVE LOGITS
     but
    2.42
     yet
    1.81
     albeit
    1.73
     if
    1.64
     or
    1.63
     although
    1.59
     and
    1.50
     almost
    1.43
     non
    1.42
     though
    1.42
    Activations Density 0.071%

    No Known Activations