© 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. 34-GEMMASCOPE-RES-131K
    7. 90465
    Prev
    Next
    INDEX
    Explanations

    words starting with Fl

    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
    effectively
    -0.78
     horsepower
    -0.74
     chickens
    -0.74
     tense
    -0.72
     Corvette
    -0.72
     belangrijkste
    -0.72
     expan
    -0.72
    itzen
    -0.71
    kamera
    -0.71
     KUR
    -0.70
    POSITIVE LOGITS
    Fl
    0.94
     FL
    0.92
    Fla
    0.84
     fluttering
    0.84
     Fla
    0.83
    FL
    0.83
     fl
    0.82
    ývá
    0.81
    amını
    0.80
     FLAC
    0.78
    Activations Density 0.062%

    No Known Activations