© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220571
    Prev
    Next
    INDEX
    Explanations

    disconnecting and engaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    芦
    0.41
    нар
    0.38
    तंत्र
    0.36
    纵
    0.36
     lashed
    0.36
    仁
    0.36
    LOLL
    0.35
     ชีวิต
    0.35
    arranty
    0.35
     laminated
    0.34
    POSITIVE LOGITS
    open
    0.38
    streng
    0.38
    TLS
    0.37
     discontinu
    0.37
    Open
    0.36
     seguimiento
    0.36
     সংযুক্ত
    0.36
     multim
    0.35
    픔
    0.35
     मेघा
    0.35
    Activations Density 0.000%

    No Known Activations