© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 65111
    Prev
    Next
    INDEX
    Explanations

    setting session

    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_53_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
    Stu
    0.38
    吐
    0.37
    PART
    0.37
     INSTR
    0.36
     Ambiental
    0.36
     IND
    0.36
     cushions
    0.36
     引
    0.35
     मिड
    0.35
    വോ
    0.35
    POSITIVE LOGITS
     topped
    0.43
    াস্থ্য
    0.41
    的美
    0.41
     davvero
    0.40
     cleanest
    0.38
     Luk
    0.38
     symmetrical
    0.38
     sucked
    0.38
     dolce
    0.38
     prettiest
    0.37
    Activations Density 0.000%

    No Known Activations