© 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. 219732
    Prev
    Next
    INDEX
    Explanations

    bid on, your safety, need to

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

    server, ruby, cultural, brand, hidden, weekly

    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
     piede
    0.50
     melewati
    0.44
     logarithms
    0.44
    togel
    0.44
    θα
    0.43
    วิธี
    0.43
     reine
    0.43
    잃
    0.43
    becomes
    0.43
     बैठकर
    0.42
    POSITIVE LOGITS
     иностран
    0.48
     Lesotho
    0.47
     считается
    0.47
     வெளி
    0.47
    ב
    0.45
    AMENTE
    0.45
     ఉత్పత్తి
    0.44
     Соответ
    0.44
    Ḥ
    0.44
    MinValue
    0.44
    Activations Density 0.001%

    No Known Activations