© 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. 98703
    Prev
    Next
    INDEX
    Explanations

    Employee Self-Service

    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
    Namara
    0.44
    <unused82>
    0.42
     ассоциа
    0.40
    Diag
    0.39
    MktCap
    0.39
    ቐ
    0.39
    嬂
    0.39
     влияния
    0.38
    譎
    0.38
     регули
    0.38
    POSITIVE LOGITS
     IT
    0.48
     Op
    0.47
     Per
    0.47
     Es
    0.45
     bir
    0.44
     ad
    0.44
     moul
    0.43
     per
    0.43
     testing
    0.43
     op
    0.43
    Activations Density 0.001%

    No Known Activations