© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29415
    Prev
    Next
    INDEX
    Explanations

    photograph description

    np_acts-logits-general · gemini-2.5-flash-lite

    Generates markdown essay titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    墘
    0.54
     recomendamos
    0.50
     גר
    0.49
     könnt
    0.49
     সুই
    0.47
     використання
    0.46
     использование
    0.46
     વેબસ
    0.46
    Puedes
    0.46
     הולנד
    0.45
    POSITIVE LOGITS
    抹
    0.42
     felon
    0.38
     kindred
    0.38
    ழு
    0.37
     narcotics
    0.37
     photograph
    0.36
     disson
    0.36
     shrinking
    0.36
     discordant
    0.36
     nascent
    0.35
    Activations Density 0.000%

    No Known Activations