© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96702
    Prev
    Next
    INDEX
    Explanations

    describing size, production, or consequences

    np_acts-logits-general · gemini-2.5-flash-lite

    oxygen therapy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     разнови
    0.48
     नाहीत
    0.47
     masterpieces
    0.47
    rauen
    0.47
    Clicked
    0.46
     찍
    0.46
    డవ
    0.46
     اوپر
    0.45
     نیچے
    0.45
     значения
    0.45
    POSITIVE LOGITS
    </em>
    0.50
     STATE
    0.48
     dobro
    0.48
     Goodman
    0.48
    /−
    0.47
     Dough
    0.46
     Nail
    0.45
     knob
    0.45
    煒
    0.45
     State
    0.44
    Activations Density 0.000%

    No Known Activations