© 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. 24457
    Prev
    Next
    INDEX
    Explanations

    RF network

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

    strong performance

    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
    at
    0.47
     kalo
    0.47
    .}}
    0.45
    POSED
    0.45
    atributo
    0.44
     Relig
    0.44
    electrical
    0.44
    al
    0.44
     Hinduism
    0.44
     मतदार
    0.44
    POSITIVE LOGITS
    дали
    0.51
     детали
    0.46
     الكريم
    0.45
     enterr
    0.44
    鞣
    0.43
    ην
    0.43
     CONDITIONS
    0.43
     соли
    0.43
     createCanvas
    0.42
     odd
    0.41
    Activations Density 0.001%

    No Known Activations