© 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. 3384
    Prev
    Next
    INDEX
    Explanations

    the word some

    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
    istiques
    2.84
    𝓱
    2.64
    zione
    2.58
    naires
    2.58
    ZIONE
    2.54
    मारक
    2.46
    ቂያ
    2.44
    㩴
    2.41
    ЕНИЕ
    2.40
    nier
    2.36
    POSITIVE LOGITS
    ۰۰
    2.82
    רות
    2.80
    ра
    2.68
    页面存档备份
    2.55
    Լ
    2.55
    very
    2.50
    white
    2.48
    ר
    2.45
    ۱۲
    2.38
    ి
    2.36
    Activations Density 0.017%

    No Known Activations