© 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. 189278
    Prev
    Next
    INDEX
    Explanations

    media and videos

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

    yet

    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
     espectacular
    0.51
     spectacularly
    0.50
     pior
    0.48
     ajuns
    0.48
     spectacular
    0.47
     hars
    0.46
     murderous
    0.46
    ག
    0.46
     comenz
    0.45
     primeros
    0.45
    POSITIVE LOGITS
    ді
    0.41
    稃
    0.38
     was
    0.38
     মূলত
    0.38
     শ্রেণ
    0.38
     Kelley
    0.38
     Media
    0.37
     গিয়েছিল
    0.37
    缓存
    0.36
     Mellon
    0.36
    Activations Density 0.005%

    No Known Activations