© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34707
    Prev
    Next
    INDEX
    Explanations

    yield

    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
    ᠂
    -2.61
    hline
    -2.28
    el
    -2.25
     него
    -2.22
     Seventeen
    -2.17
     Nineteen
    -2.17
     Fourteen
    -2.16
     technischen
    -2.16
     crowning
    -2.16
    最も
    -2.13
    POSITIVE LOGITS
     If
    2.70
    部は
    2.48
     Their
    2.38
    
    2.34
    沕
    2.27
     Heilige
    2.22
    ࿊
    2.20
    ଝ
    2.19
    它
    2.16
    ቕ
    2.13
    Activations Density 0.019%

    No Known Activations