© 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. 14849
    Prev
    Next
    INDEX
    Explanations

    essay on topic

    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
    炵
    3.15
    AnimationFrame
    3.03
     zmdi
    2.99
     findViewById
    2.95
    炲
    2.94
     getIntent
    2.93
    귋
    2.90
    뺻
    2.87
     directorio
    2.85
    cesz
    2.85
    POSITIVE LOGITS
    rub
    2.78
    istas
    2.51
    ru
    2.49
    dem
    2.48
    ay
    2.38
    ed
    2.37
    ging
    2.29
    ent
    2.28
    ing
    2.25
    fighting
    2.24
    Activations Density 0.014%

    No Known Activations