© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 21403
    Prev
    Next
    INDEX
    Explanations

    Pretty followed by common phrases

    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
    EM
    0.49
    second
    0.47
    ட்
    0.46
    <?
    0.43
    ট
    0.43
    ê
    0.42
    Ê
    0.42
    represents
    0.42
    ट
    0.41
    tf
    0.40
    POSITIVE LOGITS
    pretty
    0.59
     Pretty
    0.58
     pretty
    0.57
    Pretty
    0.53
     blonde
    0.52
     useless
    0.51
     little
    0.49
     Little
    0.48
     girl
    0.48
     pink
    0.48
    Activations Density 0.002%

    No Known Activations