© 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. 97857
    Prev
    Next
    INDEX
    Explanations

    contract terms

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

    often budget

    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
    榛
    0.54
    엠
    0.52
    绩
    0.45
    니어
    0.45
     أحد
    0.44
    约翰
    0.44
    pist
    0.44
     полі
    0.43
    纍
    0.43
    원은
    0.43
    POSITIVE LOGITS
    umen
    0.59
    iker
    0.54
     চুক্তি
    0.54
     slavery
    0.50
     layoffs
    0.50
     preaching
    0.48
     kontrak
    0.48
    ç
    0.48
    umi
    0.47
     interfering
    0.47
    Activations Density 0.000%

    No Known Activations