© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71118
    Prev
    Next
    INDEX
    Explanations

    health and human service programs

    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
     حمایت
    0.50
    investissement
    0.48
    缛
    0.47
     Patreon
    0.47
    Patent
    0.45
    理事
    0.45
     रचनात्मक
    0.45
    未来的
    0.44
     সমর্থন
    0.44
    ᡳ
    0.43
    POSITIVE LOGITS
     federally
    0.48
     STD
    0.46
     designated
    0.45
     county
    0.44
     Feder
    0.44
     program
    0.42
     all
    0.42
     regional
    0.41
     SAM
    0.41
     region
    0.41
    Activations Density 0.137%

    No Known Activations