© 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. 160613
    Prev
    Next
    INDEX
    Explanations

    allow yourServer Pluginultimately paleinto a

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

    instructions for installing packages

    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
    环境保护
    0.49
    谗
    0.48
    ن
    0.47
     строка
    0.46
    同樣
    0.45
    DO
    0.45
    DESCRIPTOR
    0.45
     VARCHAR
    0.44
    Helvetica
    0.44
    ⚠️
    0.44
    POSITIVE LOGITS
     말을
    0.47
    cedent
    0.46
    downs
    0.42
     négy
    0.42
    든
    0.42
    τού
    0.41
     생각을
    0.41
     १६
    0.41
     aDAO
    0.41
    deeds
    0.41
    Activations Density 0.001%

    No Known Activations