© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14535
    Prev
    Next
    INDEX
    Explanations

    pregnant women

    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_7_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
    ্প
    3.41
    ্স
    3.33
    ные
    3.32
    ार्थ
    3.24
    ました
    3.02
    ཌ
    3.01
    rivi
    2.95
    राधिक
    2.94
    帼
    2.88
    な
    2.84
    POSITIVE LOGITS
    eek
    2.96
    ees
    2.92
    のは
    2.88
    ото
    2.85
    eed
    2.79
    tum
    2.76
    hik
    2.56
    erk
    2.54
    smt
    2.53
    BREAK
    2.52
    Activations Density 0.023%

    No Known Activations