© 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. 73061
    Prev
    Next
    INDEX
    Explanations

    transitions study

    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
     its
    -1.78
     relata
    -1.15
    portar
    -1.13
     persil
    -1.13
    первых
    -1.12
     pulsa
    -1.07
    cupa
    -1.06
     Ambas
    -1.05
    josé
    -1.05
    satunya
    -1.05
    POSITIVE LOGITS
    Z
    1.18
    3
    1.13
    T
    1.12
    ”
    1.11
     anklicken
    1.08
    6
    1.05
    Переваги
    1.05
    N
    1.03
    -
    1.01
    Y
    1.00
    Activations Density 0.003%

    No Known Activations