© 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. 102915
    Prev
    Next
    INDEX
    Explanations

    responses starting with "Ad" or "As"

    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
     or
    -1.93
     four
    -1.77
     eight
    -1.69
     at
    -1.69
     seven
    -1.62
     five
    -1.59
     on
    -1.59
     nine
    -1.58
     six
    -1.58
     three
    -1.52
    POSITIVE LOGITS
     unending
    1.55
     quintessential
    1.54
     hugely
    1.52
    ↵
    1.48
     decidedly
    1.47
     haupts
    1.44
     Anſ
    1.40
     wondrous
    1.38
     overarching
    1.35
     revamped
    1.35
    Activations Density 0.001%

    No Known Activations