© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 160042
    Prev
    Next
    INDEX
    Explanations

    party election rallies

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obscure
    0.48
    weza
    0.46
     możesz
    0.45
     yli
    0.45
     glau
    0.45
    ဏ
    0.45
    RESOL
    0.44
     ajal
    0.44
     virulent
    0.44
    Paint
    0.43
    POSITIVE LOGITS
     партии
    0.51
    。
    0.50
     партия
    0.50
     すご
    0.46
     पार्टी
    0.45
     やっぱり
    0.45
    その他
    0.42
     जोरदार
    0.42
    stimulating
    0.42
     отрима
    0.41
    Activations Density 0.000%

    No Known Activations