© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59720
    Prev
    Next
    INDEX
    Explanations

    SHR, SHL, SHLM, SHRD formulas

    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
    isation
    -2.42
    骉
    -2.41
    暃
    -2.34
    戎
    -2.33
     現貨
    -2.25
     ещё
    -2.22
    ſelves
    -2.19
    bangun
    -2.19
     هاي
    -2.19
     aktuelle
    -2.14
    POSITIVE LOGITS
    medriver
    3.14
     "
    2.45
    ?"
    2.39
    *
    2.38
    р
    2.31
     allgemein
    2.19
    "
    2.19
    ",
    2.16
    眚
    2.11
     \_
    2.06
    Activations Density 0.001%

    No Known Activations