© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63099
    Prev
    Next
    INDEX
    Explanations

    ready to, waste your

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

    exclamations, affirmations, or beginnings

    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
    бир
    0.46
    本科
    0.44
     вполне
    0.43
     वाक्या
    0.41
    лександ
    0.41
     parochial
    0.41
    漼
    0.40
     количе
    0.40
     весьма
    0.40
     столь
    0.40
    POSITIVE LOGITS
     aktivieren
    0.49
    8
    0.46
    3
    0.46
    4
    0.45
     beforehand
    0.44
     voltaje
    0.44
    voltage
    0.44
     OLED
    0.44
     power
    0.43
    ism
    0.43
    Activations Density 0.001%

    No Known Activations