© 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. 7-GEMMASCOPE-2-RES-16K
    7. 927
    Prev
    Next
    INDEX
    Explanations

    architecture, distribution, penalties

    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
    с
    2.60
    ا
    2.53
    ty
    2.37
    𝘀
    2.35
    𝗘
    2.30
    сь
    2.23
    ౖ
    2.22
    க்கார
    2.21
    ting
    2.15
    𝘁
    2.12
    POSITIVE LOGITS
    ಛ
    2.41
    ordial
    2.41
     प्रोवाइड
    2.41
     degrés
    2.40
    ériences
    2.38
     Bürger
    2.35
     Unters
    2.33
    ীন
    2.31
    ddots
    2.30
    ınar
    2.26
    Activations Density 0.001%

    No Known Activations