© 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. 48520
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
     ovviamente
    -0.83
     الجزء
    -0.74
     ohnehin
    -0.73
    Demografia
    -0.73
    uslar
    -0.72
     geçir
    -0.72
    各样的
    -0.71
    isław
    -0.71
    asiswa
    -0.71
     advices
    -0.70
    POSITIVE LOGITS
     delight
    0.90
     específico
    0.89
     glory
    0.89
     passwords
    0.88
     regulators
    0.84
     via
    0.84
     warrant
    0.84
     wages
    0.83
     boast
    0.82
     indices
    0.81
    Activations Density 0.026%

    No Known Activations