© 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. 18047
    Prev
    Next
    INDEX
    Explanations

    descriptive text features benefits

    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
    ьо
    0.45
    ື່ອງ
    0.40
     պ
    0.40
    Voici
    0.39
    imdi
    0.38
     fondness
    0.38
     гне
    0.38
    愷
    0.38
    ቅር
    0.38
     人気
    0.37
    POSITIVE LOGITS
     transcends
    0.42
    (//
    0.38
    double
    0.37
    ليا
    0.37
    τον
    0.36
     انڈیا
    0.36
     nurture
    0.36
     double
    0.35
     empathy
    0.35
     proactively
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.