© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202775
    Prev
    Next
    INDEX
    Explanations

    deceptively simple or complex

    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
     handful
    0.49
     identifying
    0.44
    umatic
    0.43
    чины
    0.42
     uptick
    0.42
     randomized
    0.40
    riminating
    0.40
    Ｐ
    0.40
     gripping
    0.40
     escalating
    0.40
    POSITIVE LOGITS
     функции
    0.47
     удобно
    0.46
     फ्रेम
    0.45
     வச
    0.45
    파일명
    0.45
     დაკ
    0.43
     conséquence
    0.42
    tidak
    0.42
     ചെയ്യുന്നു
    0.42
     ഒഴ
    0.41
    Activations Density 0.004%

    No Known Activations