© 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. 11683
    Prev
    Next
    INDEX
    Explanations

    losing or holding ground

    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
    ள
    2.41
    aways
    2.11
     murderous
    2.09
    ला
    2.08
    끔
    2.05
     sick
    2.01
    SupportActionBar
    2.00
     ras
    1.98
    stig
    1.93
    ρ
    1.90
    POSITIVE LOGITS
    วัล
    2.15
    )—
    1.99
     quedado
    1.97
     Dropout
    1.93
     falls
    1.91
    ).—
    1.90
     бюд
    1.90
    蒾
    1.90
    Vars
    1.88
    ocurrency
    1.88
    Activations Density 0.108%

    No Known Activations