© 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. 800
    Prev
    Next
    INDEX
    Explanations

    objects and their properties

    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
     módulos
    0.55
     incompat
    0.50
     nécessairement
    0.50
     আক্রমণে
    0.49
     QUESTIONS
    0.49
    ジャ
    0.49
    譏
    0.49
    パリ
    0.48
    ᱤ
    0.48
    destroyed
    0.47
    POSITIVE LOGITS
    '
    0.57
    ing
    0.55
    ad
    0.51
    yer
    0.49
    unge
    0.49
    aan
    0.48
    ake
    0.47
    ying
    0.47
    n
    0.47
    ming
    0.46
    Activations Density 0.000%

    No Known Activations