© 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. 100515
    Prev
    Next
    INDEX
    Explanations

    Company Inc

    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
    D
    -2.81
    M
    -2.75
    F
    -2.48
    T
    -2.36
    C
    -2.36
    ーーーー
    -2.34
    P
    -2.22
    L
    -2.14
     they
    -2.08
    平常
    -2.05
    POSITIVE LOGITS
    焄
    2.75
    弍
    2.66
     Company
    2.55
    呖
    2.55
    喈
    2.44
    
    2.36
     This
    2.36
    𖥧
    2.34
    ént
    2.14
    …»
    2.13
    Activations Density 0.010%

    No Known Activations