© 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. 135431
    Prev
    Next
    INDEX
    Explanations

    applications themselves registered

    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
     assertThat
    0.42
    体が
    0.41
     gameObject
    0.41
    䚺
    0.41
    ropower
    0.39
    сказа
    0.39
    امه
    0.38
     masyarakat
    0.38
    eradish
    0.38
    ())){
    0.38
    POSITIVE LOGITS
    supervised
    0.40
    lau
    0.37
    registered
    0.35
     зу
    0.34
    삭
    0.33
    approx
    0.33
     wag
    0.33
     tare
    0.33
    cre
    0.33
    parallel
    0.33
    Activations Density 0.000%

    No Known Activations