© 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. 64381
    Prev
    Next
    INDEX
    Explanations

    randomized factorial study

    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
     أق
    -0.76
    geht
    -0.71
     Martel
    -0.69
     referrerpolicy
    -0.69
    ILE
    -0.69
     klub
    -0.69
     kong
    -0.69
     rupture
    -0.68
     LEAD
    -0.68
    ukur
    -0.67
    POSITIVE LOGITS
    Buss
    0.72
    ahua
    0.71
     cilantro
    0.69
     Incidentally
    0.64
     nhạc
    0.63
     ен
    0.62
    itorial
    0.62
    Incident
    0.62
    ("{}
    0.62
     Berwick
    0.61
    Activations Density 0.127%

    No Known Activations