© 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. 2435
    Prev
    Next
    INDEX
    Explanations

    's and ll

    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
    fps
    1.25
     predefined
    1.22
     değişken
    1.18
     ✅
    1.14
     पीरिय
    1.13
     fps
    1.12
    Definition
    1.11
     интерфей
    1.10
    ✅
    1.09
     PROCEDURE
    1.09
    POSITIVE LOGITS
    これも
    1.39
     Juga
    1.17
    那是
    1.14
    زور
    1.13
     också
    1.12
     वगैरह
    1.08
     тоже
    1.07
     rousing
    1.05
     übrigens
    1.04
    后者
    1.04
    Activations Density 0.686%

    No Known Activations