© 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. 33989
    Prev
    Next
    INDEX
    Explanations

    free followed by noun

    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
    為に
    -1.00
    しと
    -1.00
     sumamente
    -1.00
    ままで
    -0.98
     Öff
    -0.94
    ねば
    -0.94
     folgt
    -0.94
    コチラ
    -0.93
     our
    -0.92
     bewegt
    -0.91
    POSITIVE LOGITS
     of
    1.08
     is
    0.99
     TÉCNICA
    0.94
    ～～
    0.94
    技術
    0.93
    ఝ
    0.92
    ocere
    0.91
    鳥
    0.90
     They
    0.88
    фю
    0.88
    Activations Density 0.092%

    No Known Activations