© 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. 33978
    Prev
    Next
    INDEX
    Explanations

    tale about

    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
     of
    -1.23
     are
    -0.98
    ries
    -0.92
     etc
    -0.90
     neben
    -0.90
    c
    -0.88
    lh
    -0.87
     Tú
    -0.87
     والأ
    -0.87
    пр
    -0.87
    POSITIVE LOGITS
    숍
    1.23
    خرى
    1.16
     motoru
    1.09
    ächst
    1.06
     triko
    1.04
    actividad
    1.02
     bhp
    1.01
     misteriosa
    1.00
     tunik
    1.00
    Terima
    0.98
    Activations Density 0.087%

    No Known Activations