© 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. 5184
    Prev
    Next
    INDEX
    Explanations

    how many facts

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

    It detects when a user is asking a question — i.e., the start of an interrogative/asking-intent in a turn.

    oai_token-act-pair · gpt-5-miniTriggered 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
     riguarda
    0.43
    Flicky
    0.40
     mensajes
    0.39
    liğini
    0.39
    闹
    0.38
    哿
    0.37
    䢀
    0.37
     活动
    0.37
     voulez
    0.36
    ranno
    0.36
    POSITIVE LOGITS
     microorganisms
    0.42
     prokary
    0.41
     algebraic
    0.41
     eukaryotic
    0.40
     chemical
    0.40
     bacteria
    0.39
     biological
    0.39
     Fermat
    0.39
     phytoplankton
    0.38
     quarks
    0.37
    Activations Density 0.534%

    No Known Activations