© 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-65K
    7. 223
    Prev
    Next
    INDEX
    Explanations

    opacity, activate, encode

    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_65k_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
     slowmotion
    0.46
     எடை
    0.42
     подзем
    0.41
    $[\
    0.40
    ዎች
    0.39
     overloading
    0.38
     overload
    0.38
     арга
    0.38
    ഢ
    0.38
     polyd
    0.38
    POSITIVE LOGITS
    Receiver
    0.37
    roscopic
    0.36
    feed
    0.35
     পরিবেশ
    0.34
     الحكم
    0.34
     Kerr
    0.34
     director
    0.33
    Directive
    0.33
     Parole
    0.33
    ുകൊ
    0.32
    Activations Density 0.012%

    No Known Activations