© 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. 17825
    Prev
    Next
    INDEX
    Explanations

    .com, armbands, results metrics, most advanced

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

    demonstrated by

    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
    ėl
    0.44
     subcontractors
    0.44
     Incorporated
    0.44
     rural
    0.43
     Courthouse
    0.43
    ette
    0.42
     Illust
    0.42
     "
    0.42
     industry
    0.41
     komb
    0.41
    POSITIVE LOGITS
    })$.
    0.50
    Disposition
    0.48
    ذب
    0.48
    బాటు
    0.47
     dispoz
    0.47
    대가
    0.47
     pdelay
    0.46
    جا
    0.46
     ziehen
    0.46
    Magnitude
    0.46
    Activations Density 0.000%

    No Known Activations