© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 109036
    Prev
    Next
    INDEX
    Explanations

    each discussion thread

    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
     BUT
    0.45
     మరియు
    0.45
    給大家
    0.44
     Carpet
    0.44
    為了
    0.43
     ប៉ុ
    0.43
     UNITED
    0.42
    🚔
    0.40
     QUICK
    0.40
    但是在
    0.38
    POSITIVE LOGITS
     Each
    0.49
     each
    0.45
    Each
    0.43
     singularity
    0.42
     adjusts
    0.39
     wonder
    0.38
     idée
    0.38
     각
    0.38
    做到
    0.38
     perhaps
    0.37
    Activations Density 0.003%

    No Known Activations