© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10094
    Prev
    Next
    INDEX
    Explanations

    addition or indexing with plus

    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_22_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
     bırak
    1.10
     LAST
    1.03
     sot
    0.99
    Tara
    0.99
    }}-\
    0.98
     kapat
    0.98
    Subtitle
    0.97
     granddaughter
    0.97
    ﺸ
    0.97
     Logout
    0.96
    POSITIVE LOGITS
    =+
    1.53
    +:
    1.49
    +')
    1.34
    +)
    1.28
    +)$
    1.25
    +/
    1.24
    +=
    1.22
    +")
    1.22
    +}
    1.21
    _{+}
    1.19
    Activations Density 0.044%

    No Known Activations