© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33976
    Prev
    Next
    INDEX
    Explanations

    escape from or into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Protecting
    0.45
    かが
    0.44
     Camin
    0.42
    ビュー
    0.40
    保護
    0.40
    ایہ
    0.39
    安心して
    0.39
    }:${
    0.38
    तब
    0.38
    सर्गिक
    0.38
    POSITIVE LOGITS
     escape
    1.16
     escaped
    1.12
     escaping
    1.09
     escapes
    1.04
    escape
    1.02
     Escape
    1.02
    逃
    0.97
     escap
    0.91
    escaping
    0.91
     escapar
    0.90
    Activations Density 0.005%

    No Known Activations