© 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. 31-GEMMASCOPE-2-RES-262K
    7. 82601
    Prev
    Next
    INDEX
    Explanations

    non-english or specialized text

    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
     পাচ্ছেন
    0.48
     gets
    0.45
     wors
    0.45
    ígen
    0.44
    
    0.42
    provides
    0.41
    prises
    0.41
    ॔
    0.40
     undergoes
    0.40
    を得
    0.40
    POSITIVE LOGITS
     izay
    0.44
     που
    0.42
    ।
    0.42
    ow
    0.41
    abla
    0.41
     seguito
    0.40
     který
    0.39
     J
    0.38
    her
    0.38
    ank
    0.38
    Activations Density 0.001%

    No Known Activations