© 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. 39907
    Prev
    Next
    INDEX
    Explanations

    attendants, needs, described

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

    building frameworks

    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
     Dare
    0.48
     atraves
    0.46
     পদ্ধ
    0.46
    的文件
    0.45
     vivi
    0.45
     Objetivo
    0.45
     getY
    0.45
     (-)
    0.44
     الميلاد
    0.44
    ち
    0.44
    POSITIVE LOGITS
    embang
    0.47
     sculpting
    0.46
    ancing
    0.45
    ილ
    0.44
    aint
    0.43
     enhancer
    0.42
    anlage
    0.42
     customizing
    0.42
    anlı
    0.42
     interpretive
    0.41
    Activations Density 0.000%

    No Known Activations