© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8297
    Prev
    Next
    INDEX
    Explanations

    code, execution, descriptions

    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
     hed
    1.24
     COC
    1.18
     PHE
    1.16
     plaque
    1.16
     blade
    1.13
     THR
    1.10
     标准
    1.09
     带
    1.07
    トロ
    1.06
     アイス
    1.05
    POSITIVE LOGITS
    ت
    1.49
    ing
    1.39
     preguntó
    1.38
    izaje
    1.38
    UpdateRequest
    1.36
    azgo
    1.31
    proyecto
    1.27
    Opacity
    1.27
    eos
    1.27
    María
    1.27
    Activations Density 0.000%

    No Known Activations