© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130566
    Prev
    Next
    INDEX
    Explanations

    things happening step-by-step

    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_10/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
    The
    -1.58
     has
    -1.56
     when
    -1.55
     When
    -1.55
     The
    -1.51
     to
    -1.51
     if
    -1.46
     at
    -1.34
     while
    -1.32
     might
    -1.32
    POSITIVE LOGITS
    ⎯
    1.55
     mascarilla
    1.49
    
    1.42
    itisation
    1.37
     zonne
    1.36
    镡
    1.36
    艄
    1.36
     valeurs
    1.34
     niks
    1.33
     vuur
    1.32
    Activations Density 0.083%

    No Known Activations