© 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. 82044
    Prev
    Next
    INDEX
    Explanations

    definition or explanation of 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_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
     representative
    0.44
    在這個
    0.43
     predefined
    0.40
     \
    0.40
     অহ
    0.38
     landmark
    0.38
     lateral
    0.37
    정도
    0.37
    Lateral
    0.37
     Rhein
    0.37
    POSITIVE LOGITS
    安
    0.50
     stejně
    0.49
     genauso
    0.44
    św
    0.43
    problems
    0.43
     শিশুদের
    0.43
    䆔
    0.43
     ebenso
    0.42
     السعودي
    0.42
     vermutlich
    0.41
    Activations Density 0.012%

    No Known Activations