© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3315
    Prev
    Next
    INDEX
    Explanations

    standard library, original, hot water, insult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    на
    0.64
    します
    0.61
    mergeddata
    0.58
    岡田
    0.58
    คือ
    0.57
    ขาว
    0.57
    栃
    0.57
    с
    0.56
    difference
    0.55
    ↵↵
    0.54
    POSITIVE LOGITS
     avaient
    0.93
     furent
    0.90
     étaient
    0.89
     auraient
    0.86
     क्रिप्टोकरेंसी
    0.81
     quelles
    0.79
     बिटकॉइन
    0.78
    agamanam
    0.78
     autochtones
    0.77
     serait
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.