© 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. 83672
    Prev
    Next
    INDEX
    Explanations

    protection unit

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

    beneficiary information, first known, victims, training, pressure

    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
    盖
    0.53
    必须
    0.47
     alanı
    0.47
    应该
    0.46
    关系
    0.46
    应该是
    0.45
     bakan
    0.45
    观察
    0.45
    滪
    0.45
    疯狂
    0.44
    POSITIVE LOGITS
    مون
    0.43
     pessimistic
    0.42
     pawn
    0.41
    مپ
    0.40
     ربعه
    0.40
    mathbf
    0.40
     N
    0.40
    uar
    0.39
     بخ
    0.39
     yeux
    0.39
    Activations Density 0.000%

    No Known Activations