© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7922
    Prev
    Next
    INDEX
    Explanations

    cash advance, saving, flow

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

    cash flow and income

    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_53_width_65k_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
    ignes
    0.39
    iving
    0.38
    ochemistry
    0.37
    cs
    0.37
    keiten
    0.36
    capac
    0.36
     कांच
    0.36
     Ö
    0.36
    icking
    0.36
     Antigen
    0.36
    POSITIVE LOGITS
     CASH
    0.79
     Cash
    0.76
    iers
    0.72
     cash
    0.72
    Cash
    0.72
    現金
    0.69
     cow
    0.66
     strapped
    0.65
    现金
    0.64
     कैश
    0.63
    Activations Density 0.027%

    No Known Activations