© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 120724
    Prev
    Next
    INDEX
    Explanations

    seaborn import

    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
     জ্ঞানের
    0.41
    ığında
    0.40
    ێت
    0.39
    hean
    0.38
    доо
    0.37
     fasse
    0.37
     때는
    0.37
    ⃛
    0.37
     ৯ম
    0.37
     oxalate
    0.36
    POSITIVE LOGITS
     Με
    0.38
     barric
    0.35
    北
    0.35
     ricorda
    0.35
     experimentation
    0.35
    Με
    0.35
     Saccharomyces
    0.34
     Agar
    0.34
     abolition
    0.34
    AGER
    0.34
    Activations Density 0.000%

    No Known Activations