© 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. 176218
    Prev
    Next
    INDEX
    Explanations

    car rental services, cancel before, serve as provost

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

    abstract concepts or specific events

    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
     estates
    0.47
     treasures
    0.46
     embassies
    0.44
     җ
    0.43
     trusts
    0.42
    shipping
    0.42
     assigns
    0.42
    rées
    0.42
    বিশিষ্ট
    0.41
     adaptability
    0.40
    POSITIVE LOGITS
     polarizer
    0.52
     chanel
    0.47
    Radi
    0.47
    黒
    0.46
     sulfate
    0.45
    atherine
    0.44
     Marseille
    0.44
     Haifa
    0.44
     nằm
    0.43
     Chanel
    0.43
    Activations Density 0.004%

    No Known Activations