© 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. 84662
    Prev
    Next
    INDEX
    Explanations

    anchor tag attributes

    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
     golpea
    -1.86
     estudian
    -1.64
     avanzada
    -1.54
     expuesto
    -1.53
     avanzado
    -1.51
     aislada
    -1.48
     extraña
    -1.48
     arid
    -1.48
     celebró
    -1.48
    aluc
    -1.47
    POSITIVE LOGITS
    7
    1.53
    R
    1.52
    ～♪
    1.46
    9
    1.43
     вси
    1.41
     this
    1.39
    ～。
    1.38
    ～！
    1.36
     poffe
    1.34
    1
    1.34
    Activations Density 0.035%

    No Known Activations