© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    awareness, isolation, items, names

    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
    Permalink
    2.65
    u
    2.57
    ```
    2.56
    ್
    2.56
    ଞ
    2.47
    വസ്ഥ
    2.45
    ו
    2.36
    𝓪
    2.36
     semula
    2.31
    燵
    2.30
    POSITIVE LOGITS
    ்ப
    2.49
     нож
    2.46
    ын
    2.45
    னி
    2.43
     cơ
    2.42
    శ్వ
    2.38
    惕
    2.38
    getAsJsonObject
    2.37
    KIN
    2.36
    AUS
    2.35
    Activations Density 2.098%

    No Known Activations