© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210537
    Prev
    Next
    INDEX
    Explanations

    words before technical terms

    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
    ší
    0.42
    árs
    0.39
    **(
    0.39
     arbitr
    0.38
     Sterne
    0.38
     <*>
    0.38
     чему
    0.37
    㐬
    0.36
    हद
    0.36
     otten
    0.36
    POSITIVE LOGITS
    LError
    0.39
     בד
    0.38
    地产
    0.36
     οικονομ
    0.36
     部
    0.35
     Geißler
    0.35
     φυ
    0.35
     println
    0.34
     говорю
    0.34
    졔
    0.34
    Activations Density 0.001%

    No Known Activations