© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3648
    Prev
    Next
    INDEX
    Explanations

    validates harmful concepts

    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_53_width_65k_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
     Vn
    0.41
     лого
    0.40
    certification
    0.40
     pul
    0.39
     علیکم
    0.39
    頚
    0.39
     RR
    0.38
     VN
    0.38
     certification
    0.38
     credential
    0.37
    POSITIVE LOGITS
     code
    1.10
    代码
    1.05
    Code
    1.01
    code
    0.98
     Code
    0.97
     código
    0.96
    コード
    0.96
     코드
    0.93
     CODE
    0.91
    CODE
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.