© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    code context checks

    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
    <bos>
    3.09
    𝓀
    2.72
    
    2.62
    пря
    2.38
    𝕥
    2.27
    osion
    2.22
     dov
    2.19
    OHAMA
    2.19
     hígado
    2.16
    ोदय
    2.15
    POSITIVE LOGITS
     fork
    2.43
     пое
    2.41
    evil
    2.31
    ᱶ
    2.30
    et
    2.22
     teis
    2.21
     Palabra
    2.17
     кушымта
    2.16
     sürü
    2.15
    '."
    2.14
    Activations Density 0.014%

    No Known Activations