© 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. 16155
    Prev
    Next
    INDEX
    Explanations

    articles, games, dates, names

    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
    eless
    -1.10
    larda
    -1.09
    amaño
    -1.09
    zegovina
    -1.03
     şi
    -1.02
    ஸ
    -1.01
    cales
    -0.98
    一つの
    -0.98
    ſelves
    -0.97
    McLaren
    -0.96
    POSITIVE LOGITS
     were
    1.26
    CARACTER
    1.21
     tonel
    1.11
     geweldige
    1.09
     estante
    1.09
    Función
    1.09
     sereia
    1.09
    附近的
    1.07
    remember
    1.07
    both
    1.07
    Activations Density 0.127%

    No Known Activations