© 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. 5301
    Prev
    Next
    INDEX
    Explanations

    emotions and states of being preceded by prepositions

    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
     Sega
    0.27
    tl
    0.27
    hre
    0.26
    s
    0.26
    '],
    0.25
     جوړونکی
    0.25
     איך
    0.25
    ่
    0.25
     indented
    0.24
    \
    0.24
    POSITIVE LOGITS
     of
    0.45
     terhadap
    0.39
     của
    0.38
     của
    0.37
     ofthe
    0.35
    នៃការ
    0.32
     dependence
    0.32
    lessness
    0.32
    fulness
    0.31
    របស់
    0.31
    Activations Density 0.334%

    No Known Activations