© 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. 44853
    Prev
    Next
    INDEX
    Explanations

    final periods, durations, or acts

    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
    ],
    -1.87
    {
    -1.75
    (),
    -1.70
    Ibid
    -1.66
    xvii
    -1.62
    孑
    -1.61
     Also
    -1.61
    ⁷
    -1.56
    (\
    -1.55
    },
    -1.54
    POSITIVE LOGITS
    紲
    1.84
    1
    1.70
    ᕱ
    1.69
    ization
    1.69
     negru
    1.67
     sosi
    1.63
     rette
    1.60
     trist
    1.59
    ability
    1.58
    茕
    1.58
    Activations Density 0.021%

    No Known Activations