© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2426
    Prev
    Next
    INDEX
    Explanations

    pick up things

    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
    வே
    2.67
    न्नाथ
    2.59
    ige
    2.54
    eng
    2.49
    ┳
    2.39
    id
    2.38
    elsen
    2.38
    at
    2.37
    <bos>
    2.35
    ्‍य
    2.35
    POSITIVE LOGITS
    ds
    2.97
    𝗱
    2.76
     thisComponent
    2.70
     expressed
    2.69
    cter
    2.49
    𝗳
    2.49
    ીર
    2.48
    plectic
    2.47
    𝘃
    2.42
     Já
    2.42
    Activations Density 0.001%

    No Known Activations