© 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. 95084
    Prev
    Next
    INDEX
    Explanations

    decisions and observations

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

    constant interplay, rivalry, permissions, port, dress

    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
     ମ
    0.52
    不了
    0.51
     kttt
    0.49
     Những
    0.49
     utak
    0.49
     କ
    0.48
     ચૂક
    0.48
     phá
    0.47
     നേടിയ
    0.47
     
    0.47
    POSITIVE LOGITS
     integral
    0.47
     important
    0.45
    int
    0.44
     custodian
    0.44
     synchronized
    0.43
     constant
    0.42
    Carry
    0.42
    ",
    0.42
    ax
    0.42
     ambient
    0.42
    Activations Density 0.000%

    No Known Activations