© 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. 184923
    Prev
    Next
    INDEX
    Explanations

    after 'out' is 'of'

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

    explaining complex information

    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
    l
    0.49
    <0xAC>
    0.47
    bmod
    0.46
    litz
    0.46
    lhe
    0.46
    量が
    0.43
    körper
    0.43
    lord
    0.42
    pest
    0.42
    <0x91>
    0.41
    POSITIVE LOGITS
     aident
    0.54
     तिजारत
    0.51
     Extensive
    0.50
     EMERG
    0.48
     anciennes
    0.48
     atuais
    0.47
     asist
    0.47
    дея
    0.47
    ড্রিম
    0.47
     tiennent
    0.47
    Activations Density 0.000%

    No Known Activations