© 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. 34038
    Prev
    Next
    INDEX
    Explanations

    STATE followed by location

    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
    șe
    -1.02
     favoriser
    -1.00
     diversos
    -0.99
    prüfung
    -0.99
     และ
    -0.95
    ững
    -0.95
     imprimer
    -0.95
     mmHg
    -0.93
    ASR
    -0.93
    opie
    -0.92
    POSITIVE LOGITS
     could
    1.07
     amidst
    0.98
     until
    0.97
     savor
    0.94
     freuen
    0.94
     how
    0.92
     without
    0.90
     addressing
    0.89
     an
    0.89
     should
    0.89
    Activations Density 0.001%

    No Known Activations