© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12084
    Prev
    Next
    INDEX
    Explanations

    URLs and requests

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

    phrases that mark user directives or requests (often polite or emphatic) and the conversation’s turn-boundary tokens.

    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_31_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
     grammaticality
    0.49
     LaTeX
    0.47
     schoolchildren
    0.46
     interstitiis
    0.44
     millilit
    0.44
     útiles
    0.44
     alumna
    0.43
    冋
    0.43
     nanom
    0.43
    FileList
    0.42
    POSITIVE LOGITS
    0.66
    https
    0.55
    create
    0.53
    request
    0.52
    here
    0.47
    )
    0.47
    CREATE
    0.47
     https
    0.46
     ,
    0.45
    1
    0.45
    Activations Density 0.179%

    No Known Activations