© 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. 204704
    Prev
    Next
    INDEX
    Explanations

    processing bitmap images

    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
    价值观
    0.42
     ক্যাপ
    0.41
    visitor
    0.40
    তিন
    0.40
     Cinem
    0.39
    हरी
    0.39
    嗔
    0.38
    谗
    0.38
    ികിത്സ
    0.38
    옇
    0.37
    POSITIVE LOGITS
     lock
    0.44
    ׂ
    0.43
    Lock
    0.42
     स्रोत
    0.42
     locks
    0.42
     Source
    0.41
     Lock
    0.41
     Sources
    0.41
     shitty
    0.40
     hell
    0.40
    Activations Density 0.001%

    No Known Activations