© 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. 7278
    Prev
    Next
    INDEX
    Explanations

    substantial debt

    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
     séptimo
    0.74
    第五
    0.73
    বিজ্ঞ
    0.73
    чне
    0.71
     dritte
    0.69
    ViewGroup
    0.69
    </tbody>
    0.69
     الثالثه
    0.69
    TypeName
    0.69
     चौथे
    0.68
    POSITIVE LOGITS
    Alo
    0.89
     Alo
    0.89
    Fon
    0.89
     Fon
    0.85
    Ale
    0.84
     Sasha
    0.81
    𝔼
    0.81
    Aly
    0.80
     renounce
    0.80
     Fonseca
    0.78
    Activations Density 0.148%

    No Known Activations