© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9233
    Prev
    Next
    INDEX
    Explanations

    I am a/an

    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_13_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
     torr
    0.95
     ঝ
    0.94
    安定
    0.92
     Torr
    0.92
    ensia
    0.92
    eurs
    0.91
    elk
    0.90
     MMR
    0.89
     Az
    0.88
    靄
    0.88
    POSITIVE LOGITS
     imagination
    1.61
     imaginations
    1.45
     Imagination
    1.37
     customizing
    1.35
     customization
    1.34
    カスタム
    1.29
     possibilités
    1.28
    ਤ
    1.25
     creatividad
    1.24
     inventing
    1.24
    Activations Density 0.144%

    No Known Activations