© 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. 1997
    Prev
    Next
    INDEX
    Explanations

    learn, learning, learned, learns

    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
    ت
    3.06
    etrot
    3.00
    istiques
    2.80
    いった
    2.79
    istice
    2.74
    odymyr
    2.67
    etrically
    2.65
    </td>
    2.65
    ართველოს
    2.62
    тат
    2.62
    POSITIVE LOGITS
    a
    2.96
    jg
    2.66
    nt
    2.50
    rug
    2.48
    nd
    2.43
    dies
    2.42
    nds
    2.40
    _-
    2.36
    ा
    2.29
    輩
    2.25
    Activations Density 0.396%

    No Known Activations