© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1813
    Prev
    Next
    INDEX
    Explanations

    ) I quoted

    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_17_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
    ゅ
    1.04
    譚
    0.87
    ョ
    0.85
    Trem
    0.84
    ゃ
    0.84
    邝
    0.82
     Trem
    0.81
    ╫
    0.81
    ὲ
    0.81
    γων
    0.80
    POSITIVE LOGITS
     IW
    2.42
     IA
    2.38
     IM
    2.33
     IB
    2.32
     Ин
    2.26
     IG
    2.24
    イン
    2.22
     IMP
    2.21
     IE
    2.19
     IH
    2.18
    Activations Density 1.814%

    No Known Activations