© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6626
    Prev
    Next
    INDEX
    Explanations

    amounts, durations, or activities

    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
     അല്ലെങ്കിൽ
    0.37
     Nintendo
    0.33
    配件
    0.33
    ♒
    0.33
    利亚
    0.32
     passt
    0.32
    钀
    0.32
    蒎
    0.31
     निर्देशों
    0.31
    **,
    0.31
    POSITIVE LOGITS
     तीन
    0.36
     لمدة
    0.35
     dispersal
    0.35
     dispersed
    0.35
     खासा
    0.33
     duration
    0.32
     चार
    0.31
     concerted
    0.31
    ಾಗಿತ್ತು
    0.31
     four
    0.31
    Activations Density 0.002%

    No Known Activations