© 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. 260601
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    кал
    0.49
    كلمنا
    0.49
     خلال
    0.47
     durchgeführt
    0.46
    峥
    0.45
    DAG
    0.45
    யம்
    0.45
    maları
    0.44
    歧
    0.44
    傥
    0.44
    POSITIVE LOGITS
     gxf
    0.53
    👘
    0.50
     せ
    0.50
     คลิ
    0.49
     adapts
    0.49
    i
    0.49
     vadanti
    0.48
     agrees
    0.48
     옵
    0.47
     myös
    0.46
    Activations Density 0.001%

    No Known Activations