Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 8682
    Prev
    Next
    INDEX
    Explanations

    in the context of

    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_16_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
    oja
    0.28
     succede
    0.26
     don
    0.25
     lineColorSpace
    0.25
    h
    0.24
     fong
    0.24
     todas
    0.24
     coisa
    0.24
     zakład
    0.24
     fiori
    0.24
    POSITIVE LOGITS
    ك
    0.35
    ین
    0.34
    ید
    0.34
    يش
    0.33
    ling
    0.32
    на
    0.30
    G
    0.30
    پ
    0.30
    یت
    0.29
    است
    0.29
    Activations Density 0.036%

    No Known Activations