© 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. 65372
    Prev
    Next
    INDEX
    Explanations

    text recognition

    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
     deportivas
    0.45
    𝒉
    0.44
     emojis
    0.44
     randint
    0.44
    лять
    0.42
     वायर
    0.42
     Farr
    0.41
     armour
    0.41
     клуб
    0.41
    ᱲ
    0.41
    POSITIVE LOGITS
    TextBox
    0.44
    อัต
    0.43
     سریع
    0.40
    UIServer
    0.40
    Automatically
    0.40
    UIAlert
    0.40
    __."
    0.39
    ongono
    0.39
     loudly
    0.38
     زوج
    0.38
    Activations Density 0.039%

    No Known Activations