© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71059
    Prev
    Next
    INDEX
    Explanations

    invalid followed by error context

    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
     😊
    -2.56
    actéristi
    -2.50
     startling
    -2.48
     astounding
    -2.45
     hacen
    -2.44
    SOME
    -2.42
    fantastic
    -2.42
     astonishing
    -2.41
     magnificent
    -2.39
     wondrous
    -2.38
    POSITIVE LOGITS
    To
    2.84
     Surprisingly
    2.67
    Even
    2.66
    what
    2.59
    For
    2.55
    翾
    2.50
    With
    2.33
    Having
    2.31
    Just
    2.30
    Since
    2.30
    Activations Density 0.003%

    No Known Activations