© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136122
    Prev
    Next
    INDEX
    Explanations

    swallowed whole feet-first

    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_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
    Example
    0.46
    op
    0.44
     কাব্য
    0.44
     सर्वप्रथम
    0.43
    ależ
    0.43
    \_
    0.42
    Zap
    0.42
     independencia
    0.41
     البعض
    0.41
     பயிற்சிய
    0.41
    POSITIVE LOGITS
     مشتر
    0.49
     سوق
    0.44
    вающих
    0.44
     тонн
    0.44
    拃
    0.44
     nedenle
    0.43
     समाप्त
    0.42
    <unused447>
    0.41
     نہيں
    0.40
    𝑖
    0.40
    Activations Density 0.002%

    No Known Activations