© 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. 197966
    Prev
    Next
    INDEX
    Explanations

    reduction of emissions

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

    plains, density, correctly, Steel, Opus

    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
    хии
    0.50
    🕤
    0.45
     objectivity
    0.44
    jší
    0.44
    而后
    0.43
    രാ
    0.43
     გადა
    0.42
     retreating
    0.42
    退
    0.42
    шая
    0.41
    POSITIVE LOGITS
     ORNL
    0.51
    ిన
    0.47
     vuccanti
    0.47
     khô
    0.46
    ানক
    0.46
     autoclave
    0.46
     CONTROL
    0.45
     vasocon
    0.44
     Figma
    0.44
     Zn
    0.44
    Activations Density 0.001%

    No Known Activations