© 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. 14973
    Prev
    Next
    INDEX
    Explanations

    the followed by concepts

    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
     afspraak
    -1.13
    های
    -1.01
     antwoord
    -1.00
     gepubliceerd
    -0.99
     fumée
    -0.98
    cokinetic
    -0.97
    已经在
    -0.97
    大佬
    -0.96
    の場合は
    -0.95
     illustratie
    -0.94
    POSITIVE LOGITS
     how
    2.11
     about
    1.48
     possible
    1.41
     why
    1.37
     but
    1.24
     extent
    1.20
     Rechten
    1.17
     which
    1.15
     But
    1.15
     importance
    1.12
    Activations Density 0.055%

    No Known Activations