© 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. 22-GEMMASCOPE-RES-131K
    7. 25675
    Prev
    Next
    INDEX
    Explanations

    video, black, satisfaction, true, downloads

    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_22/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
     nuances
    -0.97
     тонн
    -0.91
    之人
    -0.91
    zwald
    -0.91
     हालांकि
    -0.89
     skoro
    -0.85
     Übungen
    -0.85
     должна
    -0.84
    landais
    -0.83
    /**
    -0.83
    POSITIVE LOGITS
    ̵
    0.99
    antism
    0.97
     procede
    0.93
    intera
    0.92
     laude
    0.91
    现状
    0.90
    inerario
    0.90
    stö
    0.90
    常规
    0.88
     "),
    0.88
    Activations Density 0.163%

    No Known Activations