© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 4283
    Prev
    Next
    INDEX
    Explanations

    port numbers and configurations

    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
    пати
    1.53
    ódulo
    1.43
     процедуры
    1.43
    orithm
    1.38
    分辨率
    1.35
    掑
    1.34
    処理
    1.33
    炵
    1.32
    жда
    1.32
    тап
    1.30
    POSITIVE LOGITS
     cep
    1.31
     (+)
    1.29
     alias
    1.29
     ret
    1.26
     lasted
    1.25
     Cep
    1.20
     wasn
    1.20
     ranged
    1.18
     ropes
    1.18
     berg
    1.16
    Activations Density 0.030%

    No Known Activations