© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57747
    Prev
    Next
    INDEX
    Explanations

    under one

    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
     Rien
    -0.75
     }}}{
    -0.73
    办
    -0.69
    samp
    -0.66
    Detect
    -0.66
    Ἠ
    -0.65
     suppress
    -0.65
    glises
    -0.64
    RDD
    -0.63
    McKin
    -0.63
    POSITIVE LOGITS
     Schloss
    0.77
     elapsed
    0.69
    kele
    0.68
    lbs
    0.66
    luri
    0.65
     SearchView
    0.63
    METHODS
    0.62
    НТ
    0.62
     Shopping
    0.62
    Vac
    0.62
    Activations Density 0.138%

    No Known Activations