© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1053
    Prev
    Next
    INDEX
    Explanations

    true followed by a concept

    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
    netbeans
    2.52
    unnumbered
    2.48
    𝙧
    2.33
     spontaneous
    2.28
    ה
    2.24
    ʌ
    2.20
    ருங்க
    2.20
     vif
    2.18
    iguation
    2.16
    ゥム
    2.15
    POSITIVE LOGITS
    geving
    2.77
    仡
    2.63
    .\"
    2.62
    \".
    2.57
    ,\"
    2.36
    tors
    2.34
     estate
    2.33
    imacy
    2.31
    нима
    2.26
     \"
    2.26
    Activations Density 0.779%

    No Known Activations