© 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. 146573
    Prev
    Next
    INDEX
    Explanations

    legal or warranty statements

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

    potential negative reactions

    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
    ان
    0.55
     swans
    0.51
     Shades
    0.48
     Arund
    0.48
     levers
    0.47
    াৰ
    0.47
     Sparks
    0.45
    e
    0.45
     Angle
    0.44
    ADIUM
    0.44
    POSITIVE LOGITS
     сек
    0.48
     rész
    0.48
    ienz
    0.45
    類似
    0.45
    អាច
    0.44
     letzte
    0.44
     اولاد
    0.43
    ⤷
    0.43
     zuk
    0.43
     поводу
    0.43
    Activations Density 0.001%

    No Known Activations