© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10485
    Prev
    Next
    INDEX
    Explanations

    Supervising

    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
     ;\
    1.11
    ,\,
    1.07
     }}\
    1.05
     *\
    1.04
     }}(\
    1.02
    }}}\
    1.02
    }}\
    1.02
    <0x0B>
    1.00
    }})\
    0.98
     }}(
    0.98
    POSITIVE LOGITS
    <em>
    1.01
     দুঃ
    0.83
    écie
    0.82
     hostages
    0.82
     себя
    0.80
    witness
    0.79
    ỳnh
    0.79
    īd
    0.79
    ashore
    0.78
     hine
    0.78
    Activations Density 0.000%

    No Known Activations