© 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. 33100
    Prev
    Next
    INDEX
    Explanations

    instructions and manuals

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

    instructions and commands

    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
     t
    0.75
    攏
    0.70
    {
    0.69
     u
    0.68
     intimidate
    0.68
     y
    0.68
     ramach
    0.67
     erz
    0.66
     “”
    0.66
     yakin
    0.65
    POSITIVE LOGITS
    instructions
    1.13
    directives
    0.86
    orders
    0.86
    npcs
    0.84
     instructions
    0.82
    ث
    0.82
    Instructions
    0.81
    cmds
    0.80
    делить
    0.80
    غیر
    0.79
    Activations Density 0.020%

    No Known Activations