© 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-65K
    7. 54944
    Prev
    Next
    INDEX
    Explanations

    multiplication and variable assignments

    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_65k_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
     tän
    0.45
    I
    0.44
    cett
    0.42
    Over
    0.42
    Rein
    0.42
    Hall
    0.42
    But
    0.40
    ło
    0.40
    𝙤
    0.40
    Louis
    0.40
    POSITIVE LOGITS
     decoder
    0.43
     equivalently
    0.43
     newline
    0.43
     vertex
    0.42
     dequeue
    0.41
     pathologic
    0.40
     clue
    0.39
     అదే
    0.39
     Kolmogorov
    0.39
     !=
    0.38
    Activations Density 0.002%

    No Known Activations