© 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. 65634
    Prev
    Next
    INDEX
    Explanations

    assignments and declarations

    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
     kathol
    -1.41
     cordón
    -1.17
     damaligen
    -1.14
     gameObject
    -1.10
    RotationOrder
    -1.09
     Bardzo
    -1.08
    bilden
    -1.08
     this
    -1.06
     gesamte
    -1.05
     asesinato
    -1.05
    POSITIVE LOGITS
    FONTE
    1.31
     дозво
    1.10
     Dati
    1.09
    Sébastien
    1.07
    jMenu
    1.07
     tuyo
    1.07
     modalidades
    1.06
    ică
    1.05
     Jornada
    1.05
    一手
    1.05
    Activations Density 0.018%

    No Known Activations