© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2372
    Prev
    Next
    INDEX
    Explanations

    Telugu and fine-tuning

    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_17_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
    쪼
    0.74
    الط
    0.73
    เว
    0.73
     dim
    0.73
     t
    0.73
    ສົ
    0.72
     ಗ್ರ
    0.71
    ໝ
    0.71
     h
    0.69
     cr
    0.68
    POSITIVE LOGITS
     Adidas
    1.50
    Adidas
    1.49
     Reebok
    1.48
     Disney
    1.40
     adidas
    1.39
     Nike
    1.37
     Samsung
    1.37
     Puma
    1.34
     Einstein
    1.32
    Samsung
    1.32
    Activations Density 0.576%

    No Known Activations