© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22750
    Prev
    Next
    INDEX
    Explanations

    Richmond, Corfu, Laksa

    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
     попере
    0.38
    在我们
    0.37
    𐰤
    0.37
    Late
    0.36
    頴
    0.36
    মনসিংহ
    0.35
    गन
    0.35
    小米
    0.35
     AZ
    0.35
     asserted
    0.35
    POSITIVE LOGITS
     Richmond
    0.70
    Richmond
    0.59
     Corfu
    0.52
     Jaguar
    0.44
     Jaguars
    0.44
     Jacksonville
    0.42
     コ
    0.41
     Baton
    0.41
     jaguar
    0.39
     Betfair
    0.39
    Activations Density 0.004%

    No Known Activations