© 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. 44073
    Prev
    Next
    INDEX
    Explanations

    filed under

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

    copyspace, spa, BMW, religion

    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
     βοη
    0.50
    дра
    0.47
     αποτε
    0.46
     адам
    0.46
     吃
    0.45
    }_{(
    0.45
     среднего
    0.45
     entstand
    0.44
     сопровожда
    0.44
     ἐν
    0.44
    POSITIVE LOGITS
    Explanation
    0.50
     copyspace
    0.47
    Welt
    0.45
     listings
    0.44
    افيه
    0.44
    Ứ
    0.44
    Weekend
    0.44
    BMW
    0.43
     makalah
    0.42
    Grouping
    0.42
    Activations Density 0.002%

    No Known Activations