© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13441
    Prev
    Next
    INDEX
    Explanations

    stability and instability

    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
    roughly
    2.83
    getWorld
    2.82
     ὑ
    2.77
     dentées
    2.76
    centering
    2.76
    ষুধ
    2.72
    glTranslatef
    2.66
    ளிடம்
    2.66
    quartered
    2.66
    рена
    2.64
    POSITIVE LOGITS
    ef
    2.66
    o
    2.57
    uing
    2.47
    𝐥
    2.46
    ite
    2.41
    itele
    2.40
    𝐫
    2.34
    eb
    2.33
    aaaaaaaa
    2.24
    𝐭
    2.21
    Activations Density 0.016%

    No Known Activations