© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84455
    Prev
    Next
    INDEX
    Explanations

    long term or haul

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    優れた
    -2.31
    驀
    -2.05
     parachoque
    -2.05
    引用元
    -2.03
    襠
    -2.02
     condenado
    -2.02
    注意点
    -2.02
    OUTUBE
    -2.00
    ⢅
    -1.98
    特長
    -1.98
    POSITIVE LOGITS
    ll
    3.22
    c
    2.88
    f
    2.84
    er
    2.84
    u
    2.83
    an
    2.75
    "
    2.75
    w
    2.73
    。
    2.69
    ."
    2.66
    Activations Density 0.002%

    No Known Activations