© 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. 14195
    Prev
    Next
    INDEX
    Explanations

    charts and visualization

    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
    ׁ
    2.93
    gy
    2.91
    bye
    2.88
    ging
    2.77
    END
    2.46
    end
    2.45
     end
    2.44
     spared
    2.42
    gage
    2.38
    ድግዳ
    2.33
    POSITIVE LOGITS
    aio
    3.14
    𝙡
    3.08
    𝙧
    2.92
    𝙣
    2.87
    𝙨
    2.77
    День
    2.72
    𝙘
    2.67
    𝙙
    2.65
    νει
    2.60
    𝘾
    2.59
    Activations Density 0.010%

    No Known Activations