© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29836
    Prev
    Next
    INDEX
    Explanations

    local sound after buildings

    np_acts-logits-general · gemini-2.5-flash-lite

    colonial power and expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     administrativa
    0.46
     dépôt
    0.46
    ITE
    0.45
     PROCUREMENT
    0.45
    щите
    0.44
    સાર
    0.44
    ن
    0.44
     distinguir
    0.44
    йте
    0.43
     fonte
    0.43
    POSITIVE LOGITS
    传感器
    0.48
     पिंड
    0.46
     mV
    0.43
     deseos
    0.43
    を備
    0.42
    跪
    0.41
     প্রশ্নের
    0.40
     Bây
    0.40
     হুমকির
    0.40
     Lafayette
    0.40
    Activations Density 0.000%

    No Known Activations