© 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. 101410
    Prev
    Next
    INDEX
    Explanations

    dreaming of foreign words

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

    identifies potential areas

    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
    Meter
    0.53
     اضافی
    0.50
    hte
    0.46
    Dirt
    0.44
    DataXYZ
    0.44
     одежда
    0.43
    нали
    0.42
    </strong>
    0.42
     शॉट
    0.42
    Asia
    0.42
    POSITIVE LOGITS
     halluc
    0.46
     nello
    0.46
    ೇವಿನ
    0.46
    ಷ್ಯ
    0.46
     órg
    0.45
     mortg
    0.45
     fêtes
    0.44
    ্ৰ
    0.43
     dreaming
    0.43
     affixed
    0.43
    Activations Density 0.001%

    No Known Activations