© 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. 128150
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
     obuv
    -1.11
    متن
    -1.11
    López
    -1.09
    ּוֹ
    -1.07
    zeige
    -1.05
     appeler
    -1.05
    مجموع
    -1.03
     délais
    -1.01
    ännande
    -1.01
    عنوان
    -0.99
    POSITIVE LOGITS
     there
    1.22
    ꜜ
    1.01
     they
    1.00
    erweise
    0.99
    There
    0.94
    ographically
    0.92
    mically
    0.91
     Wikipedia
    0.91
    some
    0.90
     könne
    0.90
    Activations Density 0.051%

    No Known Activations