© 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. 10780
    Prev
    Next
    INDEX
    Explanations

    Do you want to explore

    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
    s
    2.67
    ")',
    2.59
    墾
    2.31
     "/"
    2.30
    direccion
    2.27
    "}}>
    2.26
    playback
    2.25
    м
    2.24
    чете
    2.22
    "]])
    2.20
    POSITIVE LOGITS
    𝚝
    2.83
    𝚊
    2.79
    𝚘
    2.74
    𝚎
    2.50
    驒
    2.42
    lemme
    2.24
    𝚒
    2.21
    lesias
    2.18
    lig
    2.17
    ത്
    2.17
    Activations Density 0.060%

    No Known Activations