© 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. 75617
    Prev
    Next
    INDEX
    Explanations

    iOS development classes

    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
     Finder
    -1.14
    Finder
    -1.08
    Canceled
    -0.88
     finder
    -0.85
    OS
    -0.84
     Eton
    -0.78
    ⭕
    -0.78
    Lev
    -0.77
     Perci
    -0.75
    uellement
    -0.75
    POSITIVE LOGITS
    anit
    0.83
    anap
    0.76
     afternoon
    0.74
     avanzada
    0.74
     cuadrada
    0.72
    adalu
    0.70
     flight
    0.69
     deserves
    0.69
    ){\
    0.69
    曲
    0.69
    Activations Density 0.120%

    No Known Activations