© 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. 34-GEMMASCOPE-RES-131K
    4. 102749
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    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_34/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
    彪
    -0.73
    nodo
    -0.70
    ovr
    -0.69
    られていた
    -0.69
    楞
    -0.68
     Hol
    -0.68
    ):-
    -0.68
     BID
    -0.66
    Principles
    -0.64
    showthread
    -0.64
    POSITIVE LOGITS
    SY
    1.21
    ZY
    1.17
    LY
    1.14
    CY
    1.13
    zy
    1.12
    JS
    1.05
     SJ
    1.04
    MY
    1.03
    DL
    1.02
     LJ
    1.02
    Activations Density 0.041%

    No Known Activations