© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13559
    Prev
    Next
    INDEX
    Explanations

    standards and technologies

    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
     selaku
    0.44
    ренные
    0.41
     bactéries
    0.40
    <0x0B>
    0.40
     pesticides
    0.39
     contrace
    0.38
     बतौर
    0.38
     paysans
    0.38
     psychotherapy
    0.37
     portátil
    0.36
    POSITIVE LOGITS
     приходится
    0.40
     Depends
    0.39
     K
    0.38
     अलग
    0.38
     S
    0.37
     Mez
    0.37
     আলাদা
    0.37
    那麼
    0.37
     Beacon
    0.37
     Brenner
    0.36
    Activations Density 0.071%

    No Known Activations