© 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. 224878
    Prev
    Next
    INDEX
    Explanations

    technical keywords and examples

    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
    wed
    0.51
    大
    0.42
     Cuv
    0.40
    ↵
    0.38
     eff
    0.38
     cend
    0.38
    Stay
    0.36
    Pref
    0.36
     Acá
    0.36
    ague
    0.36
    POSITIVE LOGITS
    靕
    0.45
    AllFilesIn
    0.43
     fxg
    0.41
    稃
    0.41
     মার্ক
    0.41
    짬
    0.41
     쉬
    0.40
     मांसपेशियों
    0.39
     शेवट
    0.39
     Aesthetic
    0.39
    Activations Density 0.012%

    No Known Activations