© 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. 944
    Prev
    Next
    INDEX
    Explanations

    vintage tech

    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
    𝜋
    2.37
    ⃘
    2.36
    쌔
    2.35
     Здравствуйте
    2.30
    ۰
    2.24
    unprocessable
    2.21
    ب
    2.17
    ፧
    2.15
    ərbay
    2.14
    ∬
    2.12
    POSITIVE LOGITS
     folded
    2.11
     forefathers
    2.10
    lier
    2.05
     corticoster
    2.04
     childhood
    2.03
     judgment
    2.03
    lois
    2.02
     judge
    2.01
    ricted
    2.00
     enlisted
    1.97
    Activations Density 0.864%

    No Known Activations