© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 11613
    Prev
    Next
    INDEX
    Explanations

    describing purpose and function

    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_53_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
    该
    0.25
     ибо
    0.25
     거고
    0.24
    的是
    0.24
     eram
    0.23
    けど
    0.23
     ఉంట
    0.23
    だけど
    0.23
     Remember
    0.23
     eran
    0.23
    POSITIVE LOGITS
     теркәлүсез
    0.34
    <unused2173>
    0.32
     itself
    0.31
     rất
    0.29
     proved
    0.29
     została
    0.29
    <unused2152>
    0.29
     alone
    0.28
     очень
    0.28
     действительно
    0.27
    Activations Density 0.196%

    No Known Activations