© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2504
    Prev
    Next
    INDEX
    Explanations

    language borrowing

    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_7_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
     savent
    1.57
     voluntarios
    1.48
    𝘻
    1.47
    吃的
    1.44
     通知
    1.44
    𝘬
    1.41
     różnych
    1.40
     olhando
    1.38
     '(
    1.38
     camisa
    1.37
    POSITIVE LOGITS
    ernes
    1.32
    egra
    1.31
    ev
    1.30
    was
    1.28
    oc
    1.26
    颇
    1.24
    ä
    1.24
    may
    1.23
    through
    1.21
    erc
    1.18
    Activations Density 0.228%

    No Known Activations