© 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. 27582
    Prev
    Next
    INDEX
    Explanations

    manifest refraction

    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
     !!!!
    -1.59
     soooo
    -1.42
     !!!!!
    -1.41
     geringe
    -1.38
     insanely
    -1.36
     alguns
    -1.36
     centaines
    -1.35
     sooo
    -1.34
    !!!!!!!
    -1.34
     créer
    -1.34
    POSITIVE LOGITS
     even
    1.83
     severely
    1.76
     unrelenting
    1.76
     profoundly
    1.76
     extraordinarily
    1.75
    Even
    1.73
    Despite
    1.73
     strangely
    1.71
     burgeoning
    1.70
     substantially
    1.63
    Activations Density 0.002%

    No Known Activations