© 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. 10952
    Prev
    Next
    INDEX
    Explanations

    Error handling

    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
    sworth
    2.68
    কি
    2.63
    𝚏
    2.47
     wcex
    2.46
    ه‌
    2.42
    efa
    2.41
    ैन
    2.40
    ings
    2.38
    ಞ
    2.37
    ルス
    2.31
    POSITIVE LOGITS
    essayer
    2.86
    лық
    2.62
    Raised
    2.61
    γωγ
    2.52
    eek
    2.46
    ว่าง
    2.43
    crossentropy
    2.42
    COST
    2.42
    弔
    2.41
     portée
    2.39
    Activations Density 0.276%

    No Known Activations