© 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. 72040
    Prev
    Next
    INDEX
    Explanations

    invoice prices

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

    mixed language scripts and symbols

    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
    ajā
    0.55
    障
    0.53
     maple
    0.52
     गाँ
    0.52
     lactation
    0.52
    anyon
    0.52
     Athletics
    0.51
    IPE
    0.51
     sporty
    0.51
     vine
    0.50
    POSITIVE LOGITS
    سا
    0.55
    >>();
    0.48
    ၇
    0.48
    >`;
    0.46
    萨
    0.45
    گ
    0.45
    اداس
    0.44
    {}\
    0.43
    ג
    0.42
    <0x99>
    0.42
    Activations Density 0.000%

    No Known Activations