© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68915
    Prev
    Next
    INDEX
    Explanations

    DeclareMathOperator, canActivate, actions

    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
    Funktionen
    -2.14
    ónicas
    -2.09
    𐍆
    -2.02
    特点
    -2.00
     sooooo
    -1.95
     undeniably
    -1.95
     illustratie
    -1.94
     burgeoning
    -1.94
    賤
    -1.93
    爱
    -1.92
    POSITIVE LOGITS
    磲
    2.55
    ︐
    2.47
    癭
    2.39
    艄
    2.39
    辚
    2.34
    蘧
    2.25
    蠃
    2.23
    眛
    2.17
    椟
    2.16
    .”
    2.11
    Activations Density 0.000%

    No Known Activations