© 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. 154765
    Prev
    Next
    INDEX
    Explanations

    rose gold, forward your

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

    duration and frequency

    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
    abek
    0.51
     Semiconductors
    0.45
    gat
    0.44
     套
    0.43
    apex
    0.43
     edil
    0.42
    izi
    0.41
     entitlement
    0.41
    di
    0.41
    koj
    0.40
    POSITIVE LOGITS
     curtailed
    0.58
     factoring
    0.54
    раб
    0.53
    น
    0.53
    ρους
    0.52
    ালিয়া
    0.49
     cinética
    0.48
     curtail
    0.48
     تاکید
    0.48
     архівної
    0.48
    Activations Density 0.001%

    No Known Activations