© 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. 133222
    Prev
    Next
    INDEX
    Explanations

    physical descriptions and actions

    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
     ко
    0.42
     ಬೀ
    0.42
    हि
    0.40
     코
    0.40
     پار
    0.40
    쿠
    0.39
     за
    0.38
    코
    0.38
    スラ
    0.37
     빠
    0.37
    POSITIVE LOGITS
    etting
    0.41
    
    0.38
    టింగ్
    0.38
    Representation
    0.37
     rulings
    0.37
    ilien
    0.37
    ວກ
    0.37
    TabView
    0.37
    assan
    0.36
     உத்தர
    0.36
    Activations Density 0.001%

    No Known Activations