© 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. 242043
    Prev
    Next
    INDEX
    Explanations

    common control

    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
     ("
    0.49
    א
    0.48
    на
    0.47
    ".
    0.45
    二
    0.44
    ин
    0.44
     ад
    0.42
    用語
    0.42
     IRB
    0.42
     室
    0.42
    POSITIVE LOGITS
     můžete
    0.55
    🫶
    0.52
     możesz
    0.51
     จัด
    0.48
     freehold
    0.48
     ใคร
    0.47
     før
    0.46
    কমার্স
    0.46
     choisissez
    0.46
    🩷
    0.45
    Activations Density 0.001%

    No Known Activations