© 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. 9230
    Prev
    Next
    INDEX
    Explanations

    asking about learning or cancelling

    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
     nya
    2.33
     diantaranya
    2.32
     whatsapp
    2.32
     ()=>
    2.29
     굉장히
    2.26
     dibawah
    2.20
    めっちゃ
    2.19
     yg
    2.16
     diatas
    2.10
     hahaha
    2.09
    POSITIVE LOGITS
    ␥
    2.22
    ␤
    2.06
    Ϫ
    2.03
    ϩ
    1.97
    —
    1.84
    ϫ
    1.79
    ⌬
    1.78
    ].)
    1.75
    )—
    1.74
    Ⲑ
    1.69
    Activations Density 0.695%

    No Known Activations