© 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. 250976
    Prev
    Next
    INDEX
    Explanations

    academic references

    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
    begin
    0.44
    。
    0.43
    cur
    0.42
    cent
    0.42
    celes
    0.42
    <unused2004>
    0.42
    init
    0.40
    𝘤
    0.40
    Porter
    0.40
     八
    0.40
    POSITIVE LOGITS
     réaction
    0.48
    শ্ম
    0.48
     Reaction
    0.46
    utom
    0.45
     związ
    0.45
    空气
    0.45
    äische
    0.45
    ഹൃ
    0.44
     सुद्धा
    0.44
    ändern
    0.43
    Activations Density 0.001%

    No Known Activations