© 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. 5015
    Prev
    Next
    INDEX
    Explanations

    numerical data with units

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

    numeric values with decimals

    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
    nBitCount
    0.36
    BeforeText
    0.35
    禳
    0.31
     lLoginID
    0.31
    nPortIndex
    0.31
    েন্ত্র
    0.30
    lensFlare
    0.30
    <unused87>
    0.30
    沍
    0.30
    BleStatus
    0.29
    POSITIVE LOGITS
    i
    0.39
    m
    0.38
    <0x80>
    0.37
     billion
    0.37
    x
    0.37
     was
    0.37
    er
    0.36
    u
    0.36
    ↵
    0.36
    av
    0.36
    Activations Density 0.180%

    No Known Activations