© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7007
    Prev
    Next
    INDEX
    Explanations

    not complaining or interested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sufficiently
    1.01
     predecess
    1.01
    虑
    0.97
    ந்தைய
    0.96
    ographically
    0.94
     достаточно
    0.94
    ogat
    0.94
    睍
    0.93
     前回
    0.93
     ఇప్పటి
    0.92
    POSITIVE LOGITS
     sure
    1.06
    sure
    0.94
    some
    0.93
    Sure
    0.87
     somebody
    0.81
    SOME
    0.78
    Someone
    0.77
     SOME
    0.77
    same
    0.76
     some
    0.76
    Activations Density 0.105%

    No Known Activations