© 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. 8169
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
     ಆ
    0.58
     bunker
    0.50
     bunkers
    0.48
     bewildered
    0.47
     blazing
    0.46
    溘
    0.46
     stockage
    0.45
    З
    0.45
     haven
    0.45
     pristine
    0.45
    POSITIVE LOGITS
    h
    0.54
    ar
    0.53
    s
    0.52
    were
    0.51
    wl
    0.50
    vtk
    0.50
    g
    0.50
    a
    0.48
    timestamp
    0.48
    l
    0.47
    Activations Density 0.000%

    No Known Activations