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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 469
    Prev
    Next
    INDEX
    Explanations

    open concept

    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_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
     ausgel
    0.40
     끌
    0.38
    avant
    0.38
     對
    0.38
    enhanced
    0.37
    💥
    0.37
    ຖື
    0.37
    ÉE
    0.37
    ോദ
    0.36
     shrinkage
    0.36
    POSITIVE LOGITS
     open
    1.14
     Open
    1.08
     abiertos
    1.05
     terbuka
    0.96
     OPEN
    0.94
     openness
    0.93
    Open
    0.93
     abierta
    0.93
     opens
    0.91
     abierto
    0.91
    Activations Density 0.077%

    No Known Activations