© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 12489
    Prev
    Next
    INDEX
    Explanations

    C# xml documentation summary

    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
     পারেনা
    2.69
     lineHeight
    2.63
     heir
    2.47
    ᅧ
    2.44
     ARTICLES
    2.37
    ০০০
    2.28
    데요
    2.28
    дцать
    2.25
     Heraus
    2.25
    携
    2.24
    POSITIVE LOGITS
    ei
    3.59
    eeee
    3.57
    een
    3.52
    eur
    3.18
    ees
    3.05
    ev
    3.05
    eee
    3.03
    ee
    3.00
    iest
    2.96
    𝒋
    2.95
    Activations Density 0.024%

    No Known Activations