© 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. 34-GEMMASCOPE-RES-131K
    7. 1451
    Prev
    Next
    INDEX
    Explanations

    actual meaning

    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_34/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
     préalable
    -0.90
    ꯶
    -0.86
    Jura
    -0.85
    standes
    -0.85
     ?";
    -0.84
    Datasets
    -0.84
     môn
    -0.83
    homemade
    -0.81
     recrystal
    -0.81
    🏦
    -0.81
    POSITIVE LOGITS
     actual
    4.13
    actual
    3.39
    Actual
    3.19
     actually
    2.95
     eigentlichen
    2.80
     Actual
    2.80
    実際に
    2.55
     eigentliche
    2.42
     själva
    2.38
     selve
    2.36
    Activations Density 0.214%

    No Known Activations