© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10409
    Prev
    Next
    INDEX
    Explanations

    compounding interest annually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    𝟏
    1.14
    াভাব
    0.95
    empirical
    0.92
    𝟑
    0.89
    𝟐
    0.87
    SpecID
    0.87
     পাঁচ
    0.86
    StartDate
    0.84
    <unused995>
    0.83
    startX
    0.82
    POSITIVE LOGITS
     reminding
    0.87
     adding
    0.79
     sotto
    0.79
     sure
    0.79
     employing
    0.79
     afin
    0.79
     may
    0.78
     making
    0.78
     garam
    0.77
     using
    0.77
    Activations Density 0.002%

    No Known Activations