© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61456
    Prev
    Next
    INDEX
    Explanations

    Bina, Lane, pane, physicist

    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
    s
    -2.86
    ]
    -2.63
    *
    -2.53
    ub
    -2.44
    op
    -2.16
    “
    -2.09
    works
    -2.08
    www
    -2.03
    )‏
    -1.96
    no
    -1.95
    POSITIVE LOGITS
    塤
    2.16
    ṇa
    2.06
    ญี่ป
    2.02
    盦
    2.00
    妘
    2.00
    Ꭳ
    2.00
    mischen
    1.97
     vhod
    1.95
    ꔹ
    1.95
     malé
    1.93
    Activations Density 0.001%

    No Known Activations