© 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. 182568
    Prev
    Next
    INDEX
    Explanations

    describes how something works

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

    prefix "be" or "de"

    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
    зы
    0.43
     했던
    0.42
    위원
    0.42
     комфор
    0.41
    ***************
    0.41
    혀
    0.41
    ंदे
    0.40
     краси
    0.39
    갤럭시
    0.39
    팰
    0.39
    POSITIVE LOGITS
     predicament
    0.53
     financing
    0.52
     konz
    0.48
     pooling
    0.48
     varm
    0.47
     nevoie
    0.47
     mission
    0.46
     pleads
    0.46
     markt
    0.45
     phasor
    0.45
    Activations Density 0.001%

    No Known Activations