© 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. 224629
    Prev
    Next
    INDEX
    Explanations

    giant phase

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

    asking yes/no questions

    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
    दायी
    0.46
    1
    0.43
    濟
    0.43
     وكان
    0.42
     Date
    0.42
    gebra
    0.42
     Dato
    0.42
    픔
    0.41
     DATE
    0.41
     Dakota
    0.41
    POSITIVE LOGITS
     сильнее
    0.52
    ündet
    0.50
    cciones
    0.47
     इस्
    0.47
    یر
    0.47
    ologies
    0.47
    ियर
    0.47
     descuento
    0.46
     differentiated
    0.45
     entendido
    0.45
    Activations Density 0.001%

    No Known Activations