© 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. 222029
    Prev
    Next
    INDEX
    Explanations

    claim, Lord, segment, need

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

    technical processes and logic

    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
     場合
    0.55
     রস
    0.48
     حوزه
    0.48
     정의역
    0.47
    ኛውም
    0.44
     数
    0.44
     ጥቅም
    0.43
     уровнем
    0.43
     مدينه
    0.43
     巻
    0.43
    POSITIVE LOGITS
     Neal
    0.52
    :
    0.49
     Animal
    0.49
     Operation
    0.47
     deutsche
    0.47
    -
    0.47
     LAND
    0.47
     neem
    0.47
     aller
    0.47
    Neal
    0.46
    Activations Density 0.000%

    No Known Activations