© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72225
    Prev
    Next
    INDEX
    Explanations

    subjective discovery and perception

    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
     prétend
    -1.51
     vêtement
    -1.45
     rése
    -1.43
     will
    -1.38
    😺
    -1.38
     tráiler
    -1.35
     betaling
    -1.34
     регулярно
    -1.33
     konto
    -1.31
     manteau
    -1.27
    POSITIVE LOGITS
     heard
    1.54
     noticed
    1.35
     found
    1.35
     saw
    1.33
     knew
    1.28
     discovered
    1.25
     decide
    1.24
     see
    1.23
     was
    1.23
     discover
    1.22
    Activations Density 0.028%

    No Known Activations