© 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. 145010
    Prev
    Next
    INDEX
    Explanations

    city, application, stimulation

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

    options abstract

    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
    assapi
    0.52
    pregn
    0.51
    ifilm
    0.49
    ciente
    0.48
    ondata
    0.48
     وسی
    0.48
    詓
    0.48
    ensureEqual
    0.48
    ៨
    0.48
    emper
    0.47
    POSITIVE LOGITS
     fermented
    0.51
     hydrolyzed
    0.50
     substitute
    0.46
     crossorigin
    0.46
     >
    0.45
     highlight
    0.45
     vibe
    0.45
     you
    0.45
     feeling
    0.44
     Vick
    0.44
    Activations Density 0.000%

    No Known Activations