© 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. 99868
    Prev
    Next
    INDEX
    Explanations

    calculating monthly payments

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

    monthly mortgage repayments and interest rates

    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
    肄
    0.44
     உற
    0.43
    њу
    0.43
    睢
    0.41
    Integral
    0.40
    metall
    0.40
    Led
    0.40
     anys
    0.40
     ín
    0.40
    𒊭
    0.40
    POSITIVE LOGITS
     simulating
    0.49
     simulations
    0.48
     assuming
    0.47
     simulator
    0.46
     arriving
    0.46
     simulated
    0.45
     suggesting
    0.45
     corner
    0.43
     recipient
    0.41
     struggles
    0.41
    Activations Density 0.025%

    No Known Activations