© 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. 8645
    Prev
    Next
    INDEX
    Explanations

    phase 2:

    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
     Félix
    1.44
    1.43
    <em>
    1.42
     '
    1.42
    <i>
    1.39
    ‑
    1.31
    ‐
    1.30
    هی
    1.28
    aque
    1.22
     distributed
    1.21
    POSITIVE LOGITS
    曩
    2.45
    眎
    2.36
    黉
    2.19
    仳
    2.12
    畱
    2.03
    剞
    2.03
    咱们
    2.00
    慥
    1.91
    ബരിമല
    1.89
    ediakan
    1.88
    Activations Density 0.354%

    No Known Activations