© 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. 19391
    Prev
    Next
    INDEX
    Explanations

    diabetes, tuberculosis, cbd

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

    remembering things

    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
     РФ
    0.67
    翀
    0.59
    撸
    0.59
    怼
    0.57
    荭
    0.56
     گیم
    0.55
    楽曲
    0.54
     fokus
    0.54
    বছ
    0.54
     fonctionnalité
    0.53
    POSITIVE LOGITS
     prostitutes
    0.49
     mellitus
    0.48
     diabetes
    0.47
     robbers
    0.46
     (=
    0.46
     Cbd
    0.45
     prostitute
    0.45
     tuberculosis
    0.45
    這個
    0.44
     cbd
    0.44
    Activations Density 0.003%

    No Known Activations