© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 204481
    Prev
    Next
    INDEX
    Explanations

    far beyond

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

    energy density

    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
    𝔹
    0.53
    ロボ
    0.49
    これにより
    0.47
     মৃদু
    0.47
    lyPlugin
    0.46
    PopMatrix
    0.46
    ข
    0.45
    𓍊
    0.45
    คืน
    0.44
     menjalankan
    0.44
    POSITIVE LOGITS
     Directeur
    0.48
     tablo
    0.45
    ოლ
    0.44
     subsidy
    0.44
     directeur
    0.44
     nouveaux
    0.44
     jornal
    0.43
     Département
    0.42
     Envi
    0.42
     Trabalho
    0.42
    Activations Density 0.000%

    No Known Activations