© 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. 45048
    Prev
    Next
    INDEX
    Explanations

    profitable, productive, marathon, humid

    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
     dezelve
    -3.22
    呿
    -3.13
    詎
    -3.11
     zoude
    -2.83
    archiwizowane
    -2.80
    pecabe
    -2.72
    嚒
    -2.59
     ſont
    -2.45
     amazingly
    -2.45
     awesome
    -2.42
    POSITIVE LOGITS
    Most
    3.38
    Many
    3.06
    Much
    3.05
    Following
    3.02
    Like
    2.98
    While
    2.95
    Before
    2.88
    Nearly
    2.84
    With
    2.84
    Not
    2.83
    Activations Density 0.002%

    No Known Activations