© 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. 31-GEMMASCOPE-2-RES-65K
    7. 3442
    Prev
    Next
    INDEX
    Explanations

    conditional code exit

    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_31_width_65k_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
     ኣብ
    0.40
    ↵↵↵↵
    0.37
    Dame
    0.37
    ↵↵↵
    0.37
    ៕
    0.35
    ର
    0.35
     holiness
    0.34
    瀚
    0.34
     hepat
    0.33
    OMBRE
    0.33
    POSITIVE LOGITS
     परंतु
    0.46
     Then
    0.44
    omaly
    0.43
     but
    0.42
    continue
    0.40
    but
    0.40
     pero
    0.40
     তবুও
    0.40
    かもしれませんが
    0.40
     නමුත්
    0.39
    Activations Density 0.105%

    No Known Activations