© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5597
    Prev
    Next
    INDEX
    Explanations

    domain.com/

    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_13_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
     Processing
    0.87
    诒
    0.82
     Zee
    0.79
     HOWEVER
    0.79
     ~.
    0.76
     Couple
    0.75
     ●
    0.75
     -.
    0.74
     Scooter
    0.74
     通販
    0.73
    POSITIVE LOGITS
    苦手
    0.93
    密钥
    0.88
     পার্টি
    0.86
    DomainMask
    0.85
    俭
    0.85
    icore
    0.85
    roles
    0.84
    rollen
    0.84
    onomia
    0.83
    otage
    0.83
    Activations Density 0.343%

    No Known Activations