© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41131
    Prev
    Next
    INDEX
    Explanations

    illumination, transfer, agreements, language

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

    descriptions of a person physically interacting with a device—especially hand/grip actions while using a computer mouse.

    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
     provides
    0.44
     will
    0.39
     could
    0.39
     =
    0.39
     was
    0.39
     I
    0.38
     viele
    0.37
     Helper
    0.37
     Create
    0.36
     can
    0.36
    POSITIVE LOGITS
    ॉट
    0.41
    нави
    0.41
    .}$
    0.40
    ៤
    0.40
    ᒫ
    0.40
     statunit
    0.39
    гей
    0.39
     உலகில்
    0.39
     ненави
    0.38
    বীন্দ্রনাথ
    0.38
    Activations Density 0.002%

    No Known Activations