© 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. 159259
    Prev
    Next
    INDEX
    Explanations

    countries, unique, references, important

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

    distance and quantities

    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
    Medico
    0.48
     నొప్పి
    0.47
    滅
    0.47
    anso
    0.47
    vrdr
    0.47
     гря
    0.46
    rinho
    0.46
    nera
    0.46
    恥
    0.46
    wellery
    0.45
    POSITIVE LOGITS
     ≈
    0.47
     architectural
    0.45
     midpoint
    0.43
     Mid
    0.43
     midrange
    0.43
     recombinant
    0.43
     Le
    0.42
     ~
    0.42
     Resource
    0.41
     Architecture
    0.41
    Activations Density 0.000%

    No Known Activations