© 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. 72388
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast

    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
     consape
    -0.96
    rogens
    -0.93
     new
    -0.90
    HostException
    -0.90
    였
    -0.89
    ais
    -0.88
    aret
    -0.88
    ᾽
    -0.86
     progettazione
    -0.86
    demies
    -0.86
    POSITIVE LOGITS
     nevertheless
    1.41
     nonetheless
    1.29
    それでも
    1.23
    卻
    1.21
     justru
    1.04
     trotzdem
    1.01
    大丈夫です
    0.94
    Odpowiedz
    0.91
    //--
    0.88
     suscit
    0.88
    Activations Density 0.025%

    No Known Activations