© 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. 101500
    Prev
    Next
    INDEX
    Explanations

    currency and amounts

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

    mathematical formulas and calculations

    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
    睫
    0.42
    ]^{
    0.41
    ✒
    0.41
    ancel
    0.40
    éli
    0.40
    lld
    0.40
    𝑙
    0.39
    )^{
    0.39
     відді
    0.38
     fractional
    0.38
    POSITIVE LOGITS
     seventy
    0.46
     Гри
    0.45
    urahan
    0.43
     eighty
    0.42
     ۸
    0.42
    ۷
    0.41
     Assam
    0.40
    ７
    0.40
    ArgsConstructor
    0.39
    ۸
    0.39
    Activations Density 0.007%

    No Known Activations