© 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. 43752
    Prev
    Next
    INDEX
    Explanations

    information only

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

    weather patterns and explanations

    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
    bedingt
    0.44
    lahir
    0.43
     marred
    0.42
     exacerbated
    0.39
     anhand
    0.39
     islamic
    0.39
    匽
    0.39
     Islamic
    0.38
    murder
    0.38
    昏
    0.38
    POSITIVE LOGITS
     qí
    0.45
     only
    0.43
     тільки
    0.41
    设备
    0.41
     তারাই
    0.40
     двумя
    0.39
     ONLY
    0.38
     વસ્તુ
    0.38
     不需要
    0.38
     ইহা
    0.38
    Activations Density 0.000%

    No Known Activations