© 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. 250715
    Prev
    Next
    INDEX
    Explanations

    SMS drops

    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
    瑩
    0.54
    骷
    0.48
     सिनेमा
    0.46
     ControllerBase
    0.44
    SNS
    0.43
    鎧
    0.42
     přid
    0.41
    яв
    0.41
     Visualization
    0.41
    बिट
    0.40
    POSITIVE LOGITS
     belge
    0.49
     sequent
    0.49
     spect
    0.48
     unfore
    0.47
    르는
    0.46
    を選
    0.46
    Spect
    0.46
     سے
    0.45
    )
    0.45
    水を
    0.45
    Activations Density 0.000%

    No Known Activations