© 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. 120138
    Prev
    Next
    INDEX
    Explanations

    things spoken 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_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
     reconhecimento
    0.42
     ctypes
    0.41
     ARCH
    0.39
    嬅
    0.39
    pJ
    0.39
     καθη
    0.39
     riconoscimento
    0.39
    🙎
    0.39
     bindings
    0.39
     Callaghan
    0.39
    POSITIVE LOGITS
     реда
    0.39
    кс
    0.39
    Batch
    0.39
    к
    0.36
    삼
    0.36
    તા
    0.36
    нії
    0.36
    ណ្ត
    0.36
     рели
    0.35
     trained
    0.35
    Activations Density 0.001%

    No Known Activations