© 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. 58180
    Prev
    Next
    INDEX
    Explanations

    single column

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

    exploring, growth, revenue, storage

    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
     by
    0.54
     B
    0.51
     U
    0.50
     with
    0.49
     precise
    0.49
     staged
    0.49
     place
    0.49
     serviced
    0.48
     specialist
    0.48
     a
    0.48
    POSITIVE LOGITS
    хи
    0.48
    Compensation
    0.46
    стор
    0.46
    的空间
    0.45
    补偿
    0.45
    نګ
    0.45
    自身の
    0.45
    的不同
    0.45
    を受けて
    0.44
    の後
    0.44
    Activations Density 0.000%

    No Known Activations