© 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. 100246
    Prev
    Next
    INDEX
    Explanations

    list unwrap

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

    list operations

    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
    炕
    0.44
     இருக்கலாம்
    0.41
     зимо
    0.41
    Hundreds
    0.40
    Stanford
    0.40
     аласыз
    0.40
    挼
    0.40
    羌
    0.39
    जिया
    0.39
     यामध्ये
    0.39
    POSITIVE LOGITS
    lis
    0.51
    cycle
    0.45
    cycl
    0.44
     cycled
    0.42
     terrestrial
    0.41
    cycles
    0.41
     malaise
    0.41
     lis
    0.40
     cycling
    0.40
     smashed
    0.40
    Activations Density 0.000%

    No Known Activations