© 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. 41-GEMMASCOPE-2-RES-262K
    7. 102138
    Prev
    Next
    INDEX
    Explanations

    populous city, minimal story, radius squared

    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_all/layer_41_width_262k_l0_big
    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
     Rā
    0.41
     निशुल्क
    0.41
    蓖
    0.39
    騫
    0.37
     जनता
    0.36
    опера
    0.36
    桡
    0.36
     диа
    0.36
     сим
    0.36
     hoạch
    0.36
    POSITIVE LOGITS
    再び
    0.41
    OMET
    0.41
    *:
    0.39
    apit
    0.38
    推出了
    0.38
    🌩
    0.36
     novamente
    0.36
    的那
    0.35
    again
    0.35
    eben
    0.35
    Activations Density 0.304%

    No Known Activations