© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    low + quantity, price, rate, state

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

    low followed by state or quantity

    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
    र
    0.62
    يد
    0.58
    ขึ้น
    0.55
     Spear
    0.54
    лід
    0.54
     createTask
    0.53
    嶅
    0.53
    лм
    0.52
    да
    0.52
    बड़े
    0.52
    POSITIVE LOGITS
     low
    1.26
    low
    1.07
     низ
    1.07
    低的
    1.07
    低
    1.06
    LOW
    1.05
     低
    1.03
     lowest
    1.02
     thấp
    1.02
     niedrig
    1.01
    Activations Density 0.116%

    No Known Activations