© 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. 44569
    Prev
    Next
    INDEX
    Explanations

    legal, conditional, or intentional actions

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

    aes(

    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
    لیکن
    0.46
    เพิ่มเติม
    0.39
    ociaż
    0.39
     ہم
    0.39
    แก
    0.39
    ิ
    0.39
     மற்ற
    0.39
    屬於
    0.39
    ీ
    0.38
    埇
    0.38
    POSITIVE LOGITS
    <0x80>
    0.47
     computes
    0.43
    ってます
    0.42
     unwittingly
    0.42
    排序
    0.41
     parses
    0.41
     pensions
    0.40
     murder
    0.39
    wx
    0.39
     evaluate
    0.39
    Activations Density 0.005%

    No Known Activations