© 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. 64882
    Prev
    Next
    INDEX
    Explanations

    surnames with titles

    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
    with
    -1.09
     Vereine
    -1.08
     more
    -1.07
     \
    -1.04
    den
    -1.03
    ༻
    -1.03
    عث
    -1.00
     and
    -0.99
     Deixe
    -0.99
    \\
    -0.99
    POSITIVE LOGITS
    Bjs
    1.20
     plastiques
    1.17
    Galeria
    1.17
     cérami
    1.16
     deputy
    1.13
    becoming
    1.13
     selaku
    1.11
    eapples
    1.10
     Рі
    1.10
     vatten
    1.07
    Activations Density 0.060%

    No Known Activations