© 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. 23166
    Prev
    Next
    INDEX
    Explanations

    putting ourselves

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

    list items after specific punctuation

    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
     contador
    0.50
     तत्व
    0.47
     шах
    0.44
    genre
    0.43
     völl
    0.43
    ő
    0.42
    hline
    0.42
     river
    0.42
     vollständ
    0.41
     xer
    0.41
    POSITIVE LOGITS
    定的
    0.51
    Escolh
    0.48
    ామని
    0.46
    áticamente
    0.45
     Inj
    0.44
    䇝
    0.43
    弹
    0.42
    <0x0D>
    0.42
    呐
    0.42
    wounded
    0.42
    Activations Density 0.000%

    No Known Activations