© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11118
    Prev
    Next
    INDEX
    Explanations

    checkout@ actions/checkout

    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
    𝐨
    2.03
    Lead
    2.01
    𝐚
    1.84
    Consider
    1.79
     logically
    1.78
     Lead
    1.78
    }";
    1.72
    𝑜
    1.69
    relevant
    1.69
    ने
    1.68
    POSITIVE LOGITS
    iž
    1.83
     carrying
    1.80
    첼
    1.72
    ード
    1.68
     spä
    1.64
    isku
    1.64
    쩍
    1.64
    inak
    1.63
     близько
    1.60
    isk
    1.59
    Activations Density 0.000%

    No Known Activations