© 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. 57060
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas or millions/billions

    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
     both
    -1.22
     supposedly
    -1.00
     being
    -0.96
     sense
    -0.96
     not
    -0.96
     centavos
    -0.96
     only
    -0.96
     also
    -0.93
     Being
    -0.93
     seems
    -0.93
    POSITIVE LOGITS
    grazie
    0.90
     öğretmen
    0.89
     fonctionnent
    0.89
    Madre
    0.87
    Fv
    0.87
     zimowa
    0.86
     appartiennent
    0.85
    뎌
    0.85
     demandes
    0.83
    ואה
    0.83
    Activations Density 0.045%

    No Known Activations