© 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. 65897
    Prev
    Next
    INDEX
    Explanations

    class names or types

    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
     when
    -1.42
    Transcriptie
    -1.02
     where
    -0.98
    Více
    -0.96
     cuando
    -0.96
     until
    -0.96
    čnost
    -0.96
     over
    -0.95
     any
    -0.94
    ⁈
    -0.94
    POSITIVE LOGITS
    LookAnd
    1.06
    RUnlock
    1.04
     صحبت
    1.04
     “
    1.03
     $"
    0.97
     مید
    0.96
    ="
    0.96
    olesterol
    0.94
     "
    0.94
    ("
    0.89
    Activations Density 0.002%

    No Known Activations