© 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. 16394
    Prev
    Next
    INDEX
    Explanations

    PCIe, Recommended Minimum, high standards, Resource Manager

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of domain-specific technical jargon and acronyms, especially within specification-style or instructional text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     gamanam
    0.49
     prést
    0.46
     parceria
    0.45
     democracies
    0.44
    얄
    0.44
    Invitation
    0.43
    >?,
    0.43
     appartenant
    0.43
    属于
    0.42
     ecz
    0.42
    POSITIVE LOGITS
     Man
    0.52
     S
    0.48
     Tra
    0.47
    and
    0.46
     Red
    0.46
     Foundation
    0.45
     Character
    0.45
     x
    0.45
     Much
    0.44
     n
    0.44
    Activations Density 0.003%

    No Known Activations