© 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. 125867
    Prev
    Next
    INDEX
    Explanations

    multilingual or technical terms

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

    physiological differencesshapes, taxation, laws, values

    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
     comenz
    0.50
     tutors
    0.47
     sociocultural
    0.47
     begins
    0.46
     barre
    0.46
    ";}
    0.45
     intellectuals
    0.44
     earbuds
    0.44
     projectors
    0.44
    耐心
    0.43
    POSITIVE LOGITS
     ఉన్నారు
    0.50
     هەر
    0.50
     배열
    0.49
     существо
    0.48
    镕
    0.48
    женный
    0.48
     Luật
    0.48
     значения
    0.47
     Umsetzung
    0.47
    entuan
    0.47
    Activations Density 0.000%

    No Known Activations