© 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. 137883
    Prev
    Next
    INDEX
    Explanations

    account information. account information

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

    words followed by qualifiers

    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
    Leben
    0.51
    Nicht
    0.49
    ObjectTemp
    0.48
     रेगु
    0.48
    <unused342>
    0.48
    േയ
    0.47
    Aplic
    0.47
    DeviceCompliance
    0.47
    Venezuela
    0.46
    <unused670>
    0.46
    POSITIVE LOGITS
     flying
    0.53
     building
    0.52
     led
    0.48
     brick
    0.46
     io
    0.46
     to
    0.46
     fly
    0.46
     tabs
    0.45
     my
    0.45
     within
    0.45
    Activations Density 0.000%

    No Known Activations