© 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. 25735
    Prev
    Next
    INDEX
    Explanations

    resetting after trouble

    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
    zata
    -0.83
    OPTIONAL
    -0.82
    Disliked
    -0.81
    alike
    -0.81
    Installed
    -0.79
    Estad
    -0.77
     eikä
    -0.76
    あたり
    -0.76
     genauso
    -0.71
     omdat
    -0.71
    POSITIVE LOGITS
     then
    1.95
     thereafter
    1.59
     after
    1.48
     thus
    1.47
     afterwards
    1.39
     once
    1.38
     still
    1.35
     thereupon
    1.34
     afterward
    1.33
    それでも
    1.30
    Activations Density 0.105%

    No Known Activations