© 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. 6069
    Prev
    Next
    INDEX
    Explanations

    sequence after `This`

    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
     পেয়েছিলাম
    1.13
    ☺️
    1.03
     کررہ
    1.02
    今まで
    1.00
     cuz
    0.96
    BOOKS
    0.93
    ajna
    0.92
    😊
    0.92
     Mahomes
    0.90
    週
    0.90
    POSITIVE LOGITS
     Specifies
    1.43
     Jeśli
    1.27
     möglicherweise
    1.27
     或
    1.24
    <bbox>
    1.24
     enthält
    1.22
     用于
    1.20
     optionally
    1.20
    可选
    1.20
    用于
    1.19
    Activations Density 0.139%

    No Known Activations