© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70353
    Prev
    Next
    INDEX
    Explanations

    "use strict";

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <b>
    -1.78
     would
    -1.49
     of
    -1.36
     like
    -1.29
    TestingModule
    -1.23
    {
    -1.23
    </h1>
    -1.17
    หญิง
    -1.17
    ⁡
    -1.16
    eddings
    -1.16
    POSITIVE LOGITS
    噚
    1.46
     joga
    1.28
    нави
    1.28
    சிய
    1.24
    őség
    1.24
    tadiene
    1.23
     gesagt
    1.22
     artikkeli
    1.21
     Subsection
    1.21
    Kjelder
    1.21
    Activations Density 1.086%

    No Known Activations