© 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. 91483
    Prev
    Next
    INDEX
    Explanations

    placeholder values

    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
     Barriers
    -0.71
    Воспита
    -0.71
     Lul
    -0.69
     inter
    -0.68
     exponents
    -0.68
     Bumper
    -0.68
     reasons
    -0.68
     控
    -0.67
     attempts
    -0.66
     Lösungs
    -0.65
    POSITIVE LOGITS
    Place
    0.98
    Placeholder
    0.92
     PLACE
    0.91
     Place
    0.90
    placeholder
    0.90
     place
    0.84
     placeholder
    0.84
    feeding
    0.84
    zieh
    0.81
     Utama
    0.81
    Activations Density 0.009%

    No Known Activations