© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41662
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and specific entities

    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_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
     계속
    0.52
     वैश्विक
    0.45
     참
    0.45
     глоба
    0.44
    គឺ
    0.43
    continues
    0.43
    icientes
    0.43
     প্রাধান্য
    0.43
     विकल्प
    0.43
     약
    0.42
    POSITIVE LOGITS
     permettent
    0.46
    𝕋
    0.45
     pequenas
    0.45
     eléctrica
    0.45
     internes
    0.44
     parf
    0.44
     donuts
    0.43
     électriques
    0.43
     furent
    0.41
     Dock
    0.41
    Activations Density 0.001%

    No Known Activations