© 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. 31-GEMMASCOPE-2-RES-262K
    7. 110223
    Prev
    Next
    INDEX
    Explanations

    We have detected unusual activity

    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_31_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
    popupIsOpen
    0.49
    は
    0.49
    }=-\
    0.46
    essentially
    0.46
    損
    0.45
    ellular
    0.45
    }=(
    0.45
    ້າ
    0.45
    ல்களை
    0.44
    а
    0.44
    POSITIVE LOGITS
    此同时
    0.55
     Seasonal
    0.54
     Vaccination
    0.54
     Medical
    0.52
     Student
    0.52
     triathlon
    0.50
     Hair
    0.50
     immunization
    0.50
     vaccination
    0.49
     pudieran
    0.49
    Activations Density 0.007%

    No Known Activations