© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10325
    Prev
    Next
    INDEX
    Explanations

    space, containment, confinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &
    0.93
    dua
    0.92
     linear
    0.92
    0
    0.89
     piano
    0.88
    eller
    0.87
     laser
    0.87
    $
    0.84
    $&
    0.84
    &
    0.82
    POSITIVE LOGITS
     enveloping
    1.20
     encirc
    1.12
     ሽፋን
    1.08
     contenedor
    1.06
     confines
    1.02
     пространство
    1.00
     공간
    1.00
     đựng
    0.99
     confinement
    0.96
     confining
    0.96
    Activations Density 0.546%

    No Known Activations