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. 40-GEMMASCOPE-2-RES-262K
    4. 18852
    Prev
    Next
    INDEX
    Explanations

    compile commands with -o

    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_40_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
    يمق
    0.38
    irani
    0.36
    ylon
    0.36
    ἕ
    0.35
    estabelecimento
    0.35
     മുഴ
    0.35
     speculators
    0.35
     reserva
    0.34
    ூன்
    0.34
    ПР
    0.33
    POSITIVE LOGITS
     Tampa
    0.38
     wandered
    0.38
    ەل
    0.38
    ğa
    0.37
     elegantly
    0.37
    *}$
    0.37
    给我
    0.36
    /**/*.
    0.36
     Trinidad
    0.36
     তা
    0.36
    Activations Density 0.001%

    No Known Activations