© 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. 133041
    Prev
    Next
    INDEX
    Explanations

    date fields

    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
     Sprint
    0.42
    苚
    0.38
    placeholder
    0.38
    ________________
    0.38
     nourr
    0.38
     =\
    0.36
     usages
    0.36
    न्हे
    0.36
     Rajesh
    0.35
    ologico
    0.35
    POSITIVE LOGITS
    Score
    0.40
    Scores
    0.40
    武
    0.40
    score
    0.39
    Letter
    0.39
    Cone
    0.39
    Kale
    0.39
    Minute
    0.39
    чення
    0.38
    字母
    0.37
    Activations Density 0.003%

    No Known Activations