© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2106
    Prev
    Next
    INDEX
    Explanations

    Robot, TO, The

    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
     caminar
    -0.85
    dula
    -0.83
     walking
    -0.77
    iy
    -0.75
    präche
    -0.72
     CDF
    -0.71
     minY
    -0.71
     georgia
    -0.71
     {?
    -0.70
    ggars
    -0.69
    POSITIVE LOGITS
     nig
    0.84
    tigt
    0.82
    zü
    0.80
     Ng
    0.77
     Espagne
    0.76
     regres
    0.75
    Aless
    0.75
     Dies
    0.74
     correlates
    0.72
    绝望
    0.72
    Activations Density 0.001%

    No Known Activations