© 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. 48062
    Prev
    Next
    INDEX
    Explanations

    walk pace tempo shortcut

    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
    aná
    0.42
     delas
    0.41
     पास
    0.41
     (<
    0.41
    透過
    0.39
     hak
    0.39
     marginLeft
    0.39
     Pasal
    0.38
    透过
    0.38
     <
    0.38
    POSITIVE LOGITS
     sviluppo
    0.49
    ท
    0.47
     généralement
    0.46
     nieve
    0.45
     cheery
    0.44
    พ
    0.44
    蕉
    0.44
    르
    0.43
     pueblos
    0.43
     observación
    0.42
    Activations Density 0.013%

    No Known Activations