© 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. 115372
    Prev
    Next
    INDEX
    Explanations

    fresh and new

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

    phrases ending in after / :

    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
     전달
    0.52
    진
    0.50
    각
    0.49
    지의
    0.47
    ხედ
    0.47
    교육
    0.47
    라마
    0.46
    方的
    0.46
    焐
    0.46
    щего
    0.45
    POSITIVE LOGITS
     h
    0.51
     le
    0.49
     zh
    0.49
     l
    0.47
     penned
    0.47
     di
    0.45
     vien
    0.45
    ot
    0.44
     mil
    0.44
     tu
    0.44
    Activations Density 0.001%

    No Known Activations