© 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. 7048
    Prev
    Next
    INDEX
    Explanations

    specific terms followed by location/relation

    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
     सबका
    0.38
     köny
    0.38
    本書
    0.36
     книга
    0.36
    ార్థ
    0.36
    𝗅
    0.36
     ছবির
    0.35
     лучшие
    0.35
     పుస్త
    0.35
     planen
    0.35
    POSITIVE LOGITS
     of
    0.66
     from
    0.64
     belonging
    0.50
     in
    0.49
     pertaining
    0.49
     for
    0.49
     on
    0.49
     của
    0.48
     located
    0.46
     ở
    0.45
    Activations Density 0.302%

    No Known Activations