© 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. 1270
    Prev
    Next
    INDEX
    Explanations

    F(number) or r(letter)

    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
     when
    -2.33
     If
    -1.93
     which
    -1.88
     if
    -1.82
     whose
    -1.73
     would
    -1.67
     where
    -1.64
     for
    -1.63
     might
    -1.63
     could
    -1.59
    POSITIVE LOGITS
    9
    1.95
    8
    1.84
    7
    1.81
    0
    1.70
     doivent
    1.49
    6
    1.48
     inim
    1.45
    4
    1.41
    5
    1.39
    3
    1.27
    Activations Density 0.004%

    No Known Activations