© 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. 222186
    Prev
    Next
    INDEX
    Explanations

    expensive items and specific categories

    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
    રિ
    0.45
    ार्मिक
    0.44
     guidebook
    0.42
    relationship
    0.39
    సుకొ
    0.39
     considerazione
    0.38
     decrypted
    0.38
     ና
    0.38
    ั่วโมง
    0.38
    উঠ
    0.38
    POSITIVE LOGITS
     McNeil
    0.47
     Whelan
    0.42
     carros
    0.41
    inert
    0.39
     Mick
    0.37
     senjata
    0.36
     Sheeran
    0.36
     blades
    0.35
    irão
    0.35
     Band
    0.35
    Activations Density 0.000%

    No Known Activations