© 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. 158849
    Prev
    Next
    INDEX
    Explanations

    space availability

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

    qualitative description

    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
     dilakukan
    0.46
     每
    0.45
     obil
    0.44
     可
    0.44
     parecía
    0.44
     tentunya
    0.43
     nacido
    0.43
     doen
    0.43
    );">
    0.43
     elég
    0.43
    POSITIVE LOGITS
    three
    0.52
     falsely
    0.47
    nearest
    0.46
    Nearest
    0.45
     служ
    0.45
    South
    0.44
    楡
    0.44
    ۴
    0.44
    wreck
    0.44
    sighted
    0.43
    Activations Density 0.001%

    No Known Activations