© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4243
    Prev
    Next
    INDEX
    Explanations

    how management

    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_13_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
    য়া
    0.90
    深深
    0.86
     longstanding
    0.86
     longtime
    0.86
    ңү
    0.85
    lash
    0.84
    姥
    0.83
    麻烦
    0.82
    悪い
    0.81
    シルバー
    0.81
    POSITIVE LOGITS
     HTTP
    1.20
     Córdoba
    1.17
     Params
    1.16
     España
    1.15
     Belg
    1.14
     கைப்ப
    1.12
     Messi
    1.12
     polinom
    1.11
     gov
    1.11
     norme
    1.10
    Activations Density 0.000%

    No Known Activations