© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23900
    Prev
    Next
    INDEX
    Explanations

    leap year logic

    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
     prophylactic
    0.42
    캅
    0.39
    騙
    0.37
     uric
    0.37
     biota
    0.36
     drug
    0.36
    angkap
    0.36
     ragione
    0.35
    グラム
    0.35
     glyc
    0.35
    POSITIVE LOGITS
     உறு
    0.45
    㡺
    0.41
     कों
    0.40
    rés
    0.40
    much
    0.40
     WPS
    0.40
    ลา
    0.39
     Keep
    0.39
     Rish
    0.39
     Origin
    0.38
    Activations Density 0.000%

    No Known Activations