© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7583
    Prev
    Next
    INDEX
    Explanations

    i can do X

    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
    <unused337>
    1.58
    鿢
    1.57
     assertions
    1.51
     infliction
    1.48
    asaddo
    1.47
    ꗟ
    1.47
    apetva
    1.44
    ꗤ
    1.44
     disbursement
    1.41
    <unused1207>
    1.40
    POSITIVE LOGITS
     reportedly
    0.97
     indeed
    0.89
     ​​
    0.83
     unfortunately
    0.79
     partially
    0.78
    <0xC2>
    0.78
     partly
    0.76
     definitely
    0.76
    <sup>
    0.75
    <em>
    0.74
    Activations Density 0.704%

    No Known Activations