© 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. 34-GEMMASCOPE-RES-131K
    7. 3201
    Prev
    Next
    INDEX
    Explanations

    topics and titles

    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_34/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
     však
    -0.93
    randomUUID
    -0.89
     étape
    -0.88
     IconData
    -0.88
    PickerController
    -0.87
    xpress
    -0.86
    iori
    -0.85
     OTHERWISE
    -0.85
     зимо
    -0.84
     as
    -0.84
    POSITIVE LOGITS
    ],
    1.05
    "],
    0.85
    Align
    0.84
     существует
    0.81
     thwarted
    0.80
    oriam
    0.79
     בישראל
    0.79
     ],
    0.78
    ].
    0.77
    bisa
    0.77
    Activations Density 0.000%

    No Known Activations