© 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. 104405
    Prev
    Next
    INDEX
    Explanations

    peripher

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

    simulation, worlds, control

    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
     organise
    0.58
    фикации
    0.56
    }+...+\
    0.56
    organiser
    0.54
    vale
    0.51
     осень
    0.51
    ense
    0.50
    atul
    0.50
    ‌లో
    0.50
     insolvency
    0.50
    POSITIVE LOGITS
    خ
    0.54
     peripher
    0.46
    ೃಹ
    0.45
     محیط
    0.45
    釈
    0.44
    プレ
    0.43
     peripheral
    0.43
    سین
    0.43
    ည
    0.42
     سین
    0.41
    Activations Density 0.000%

    No Known Activations