© 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. 40-GEMMASCOPE-2-RES-262K
    7. 220570
    Prev
    Next
    INDEX
    Explanations

    legal and structural terms

    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
    ინის
    0.42
    陼
    0.40
     Redistributions
    0.39
     ningún
    0.39
     nenhum
    0.38
    arynx
    0.38
    加坡
    0.38
    ാൻ
    0.37
    wegs
    0.37
    郃
    0.37
    POSITIVE LOGITS
    should
    0.37
    these
    0.37
    Carp
    0.36
     should
    0.36
     PropTypes
    0.36
    Strateg
    0.36
     effective
    0.35
    Phys
    0.34
    Nik
    0.34
     Nikola
    0.34
    Activations Density 0.001%

    No Known Activations