© 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. 41-GEMMASCOPE-2-RES-262K
    7. 62269
    Prev
    Next
    INDEX
    Explanations

    Highveld, TexturePacker, shader, cities, Eastern

    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_all/layer_41_width_262k_l0_big
    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
     discontinued
    0.40
     उपराष्ट्रपति
    0.39
    嚇
    0.38
    लेन
    0.37
    escal
    0.37
     Pretoria
    0.36
     крепо
    0.36
    routes
    0.36
     escal
    0.36
    一副
    0.36
    POSITIVE LOGITS
     ভট্টাচার্য
    0.42
     दुर्गेश
    0.41
    ophora
    0.40
     MDC
    0.39
    Density
    0.38
     몰
    0.38
    衤
    0.37
    dagger
    0.37
    imgInit
    0.37
     dense
    0.37
    Activations Density 0.001%

    No Known Activations