© 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. 71940
    Prev
    Next
    INDEX
    Explanations

    awards, electronic, radiation, attracting

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

    normally describes a contrast

    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
     cache
    0.49
     Museu
    0.47
     mock
    0.46
    ַ
    0.46
    🕌
    0.46
    บา
    0.46
     bogus
    0.46
     způsob
    0.45
     salió
    0.44
    疙
    0.44
    POSITIVE LOGITS
     elektronik
    0.45
     Occasionally
    0.44
    Outside
    0.44
    asks
    0.44
     சிறிது
    0.43
     स्थानिक
    0.43
     전자
    0.42
     इलेक्ट्रॉनिक
    0.41
     Elektron
    0.41
     Radiation
    0.40
    Activations Density 0.000%

    No Known Activations