© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136554
    Prev
    Next
    INDEX
    Explanations

    beginning and ending financial states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creditors
    0.55
     payroll
    0.53
     debt
    0.52
     asset
    0.52
     creditor
    0.51
     accrue
    0.49
    債
    0.49
    资产
    0.49
     financed
    0.49
    財
    0.49
    POSITIVE LOGITS
     Beginning
    0.65
    Beginning
    0.58
     beginning
    0.54
    beginning
    0.51
     Anfang
    0.49
    Ending
    0.48
     Ending
    0.47
    ending
    0.46
     Brought
    0.46
     Sales
    0.44
    Activations Density 0.016%

    No Known Activations