© 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. 73797
    Prev
    Next
    INDEX
    Explanations

    hang or hang out

    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
    呖
    -2.23
    躄
    -2.02
    が取
    -1.82
     verhindern
    -1.79
    釹
    -1.77
    짭
    -1.71
    齶
    -1.70
    笋
    -1.70
    GEBURTS
    -1.67
    ERTO
    -1.66
    POSITIVE LOGITS
    ]
    2.03
     an
    1.96
     in
    1.96
     =
    1.84
     ‘
    1.82
    núť
    1.78
     the
    1.76
    猡
    1.74
    灕
    1.73
     a
    1.70
    Activations Density 0.004%

    No Known Activations