© 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. 157902
    Prev
    Next
    INDEX
    Explanations

    financial figures and quantities

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

    when followed by context

    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
    帥
    0.43
     catchy
    0.41
     soldier
    0.40
    ติ
    0.39
    耸
    0.39
    掃
    0.38
    莘
    0.38
    ይም
    0.38
    ֣
    0.37
     Graduation
    0.37
    POSITIVE LOGITS
     servidores
    0.57
     estudos
    0.56
     francesa
    0.54
     apresent
    0.52
     país
    0.52
     buscar
    0.51
     apresentar
    0.51
     tomar
    0.49
     estimular
    0.49
     IPA
    0.49
    Activations Density 0.000%

    No Known Activations