© 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. 91863
    Prev
    Next
    INDEX
    Explanations

    case identifiers and numbers

    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
     boiling
    -0.79
    時から
    -0.73
     Lä
    -0.72
     solvent
    -0.70
     sued
    -0.70
     lawsuits
    -0.69
     Solutions
    -0.69
     рождения
    -0.68
     Atlantic
    -0.68
     Konto
    -0.67
    POSITIVE LOGITS
     tox
    0.74
    regate
    0.72
    árqu
    0.67
    regated
    0.66
    CPA
    0.66
     colt
    0.65
     Ska
    0.65
     CPA
    0.65
     Körpers
    0.64
     Američ
    0.64
    Activations Density 0.082%

    No Known Activations